diff options
Diffstat (limited to 'kernel')
146 files changed, 11265 insertions, 3953 deletions
diff --git a/kernel/Kconfig.kexec b/kernel/Kconfig.kexec index 946dffa048b7..6c34e63c88ff 100644 --- a/kernel/Kconfig.kexec +++ b/kernel/Kconfig.kexec @@ -2,11 +2,13 @@ menu "Kexec and crash features" -config CRASH_CORE +config CRASH_RESERVE + bool + +config VMCORE_INFO bool config KEXEC_CORE - select CRASH_CORE bool config KEXEC_ELF @@ -95,9 +97,11 @@ config KEXEC_JUMP config CRASH_DUMP bool "kernel crash dumps" + default y depends on ARCH_SUPPORTS_CRASH_DUMP - select CRASH_CORE - select KEXEC_CORE + depends on KEXEC_CORE + select VMCORE_INFO + select CRASH_RESERVE help Generate crash dump after being started by kexec. This should be normally only set in special crash dump kernels diff --git a/kernel/Makefile b/kernel/Makefile index ce105a5558fc..3c13240dfc9f 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -68,8 +68,10 @@ obj-$(CONFIG_MODULE_SIG_FORMAT) += module_signature.o obj-$(CONFIG_KALLSYMS) += kallsyms.o obj-$(CONFIG_KALLSYMS_SELFTEST) += kallsyms_selftest.o obj-$(CONFIG_BSD_PROCESS_ACCT) += acct.o -obj-$(CONFIG_CRASH_CORE) += crash_core.o +obj-$(CONFIG_VMCORE_INFO) += vmcore_info.o elfcorehdr.o +obj-$(CONFIG_CRASH_RESERVE) += crash_reserve.o obj-$(CONFIG_KEXEC_CORE) += kexec_core.o +obj-$(CONFIG_CRASH_DUMP) += crash_core.o obj-$(CONFIG_KEXEC) += kexec.o obj-$(CONFIG_KEXEC_FILE) += kexec_file.o obj-$(CONFIG_KEXEC_ELF) += kexec_elf.o @@ -120,7 +122,6 @@ obj-$(CONFIG_PERF_EVENTS) += events/ obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o obj-$(CONFIG_PADATA) += padata.o -obj-$(CONFIG_CRASH_DUMP) += crash_dump.o obj-$(CONFIG_JUMP_LABEL) += jump_label.o obj-$(CONFIG_CONTEXT_TRACKING) += context_tracking.o obj-$(CONFIG_TORTURE_TEST) += torture.o diff --git a/kernel/async.c b/kernel/async.c index 97f224a5257b..4c3e6a44595f 100644 --- a/kernel/async.c +++ b/kernel/async.c @@ -64,6 +64,7 @@ static async_cookie_t next_cookie = 1; static LIST_HEAD(async_global_pending); /* pending from all registered doms */ static ASYNC_DOMAIN(async_dfl_domain); static DEFINE_SPINLOCK(async_lock); +static struct workqueue_struct *async_wq; struct async_entry { struct list_head domain_list; @@ -174,7 +175,7 @@ static async_cookie_t __async_schedule_node_domain(async_func_t func, spin_unlock_irqrestore(&async_lock, flags); /* schedule for execution */ - queue_work_node(node, system_unbound_wq, &entry->work); + queue_work_node(node, async_wq, &entry->work); return newcookie; } @@ -345,3 +346,17 @@ bool current_is_async(void) return worker && worker->current_func == async_run_entry_fn; } EXPORT_SYMBOL_GPL(current_is_async); + +void __init async_init(void) +{ + /* + * Async can schedule a number of interdependent work items. However, + * unbound workqueues can handle only upto min_active interdependent + * work items. The default min_active of 8 isn't sufficient for async + * and can lead to stalls. Let's use a dedicated workqueue with raised + * min_active. + */ + async_wq = alloc_workqueue("async", WQ_UNBOUND, 0); + BUG_ON(!async_wq); + workqueue_set_min_active(async_wq, WQ_DFL_ACTIVE); +} diff --git a/kernel/audit.c b/kernel/audit.c index 9c8e5f732c4c..e7a62ebbf4d1 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -1693,9 +1693,7 @@ static int __init audit_init(void) if (audit_initialized == AUDIT_DISABLED) return 0; - audit_buffer_cache = kmem_cache_create("audit_buffer", - sizeof(struct audit_buffer), - 0, SLAB_PANIC, NULL); + audit_buffer_cache = KMEM_CACHE(audit_buffer, SLAB_PANIC); skb_queue_head_init(&audit_queue); skb_queue_head_init(&audit_retry_queue); diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index 8317a37dea0b..be8c680121e4 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -788,7 +788,7 @@ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) static inline int audit_dupe_lsm_field(struct audit_field *df, struct audit_field *sf) { - int ret = 0; + int ret; char *lsm_str; /* our own copy of lsm_str */ diff --git a/kernel/backtracetest.c b/kernel/backtracetest.c index 370217dd7e39..a4181234232b 100644 --- a/kernel/backtracetest.c +++ b/kernel/backtracetest.c @@ -21,24 +21,20 @@ static void backtrace_test_normal(void) dump_stack(); } -static DECLARE_COMPLETION(backtrace_work); - -static void backtrace_test_irq_callback(unsigned long data) +static void backtrace_test_bh_workfn(struct work_struct *work) { dump_stack(); - complete(&backtrace_work); } -static DECLARE_TASKLET_OLD(backtrace_tasklet, &backtrace_test_irq_callback); +static DECLARE_WORK(backtrace_bh_work, &backtrace_test_bh_workfn); -static void backtrace_test_irq(void) +static void backtrace_test_bh(void) { - pr_info("Testing a backtrace from irq context.\n"); + pr_info("Testing a backtrace from BH context.\n"); pr_info("The following trace is a kernel self test and not a bug!\n"); - init_completion(&backtrace_work); - tasklet_schedule(&backtrace_tasklet); - wait_for_completion(&backtrace_work); + queue_work(system_bh_wq, &backtrace_bh_work); + flush_work(&backtrace_bh_work); } #ifdef CONFIG_STACKTRACE @@ -65,7 +61,7 @@ static int backtrace_regression_test(void) pr_info("====[ backtrace testing ]===========\n"); backtrace_test_normal(); - backtrace_test_irq(); + backtrace_test_bh(); backtrace_test_saved(); pr_info("====[ end of backtrace testing ]====\n"); diff --git a/kernel/bounds.c b/kernel/bounds.c index b529182e8b04..c5a9fcd2d622 100644 --- a/kernel/bounds.c +++ b/kernel/bounds.c @@ -19,7 +19,7 @@ int main(void) DEFINE(NR_PAGEFLAGS, __NR_PAGEFLAGS); DEFINE(MAX_NR_ZONES, __MAX_NR_ZONES); #ifdef CONFIG_SMP - DEFINE(NR_CPUS_BITS, ilog2(CONFIG_NR_CPUS)); + DEFINE(NR_CPUS_BITS, bits_per(CONFIG_NR_CPUS)); #endif DEFINE(SPINLOCK_SIZE, sizeof(spinlock_t)); #ifdef CONFIG_LRU_GEN diff --git a/kernel/bpf/Kconfig b/kernel/bpf/Kconfig index 6a906ff93006..bc25f5098a25 100644 --- a/kernel/bpf/Kconfig +++ b/kernel/bpf/Kconfig @@ -3,6 +3,7 @@ # BPF interpreter that, for example, classic socket filters depend on. config BPF bool + select CRYPTO_LIB_SHA1 # Used by archs to tell that they support BPF JIT compiler plus which # flavour. Only one of the two can be selected for a specific arch since diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index f526b7573e97..368c5d86b5b7 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -6,7 +6,7 @@ cflags-nogcse-$(CONFIG_X86)$(CONFIG_CC_IS_GCC) := -fno-gcse endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o log.o token.o obj-$(CONFIG_BPF_SYSCALL) += bpf_iter.o map_iter.o task_iter.o prog_iter.o link_iter.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o @@ -15,6 +15,9 @@ obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o obj-$(CONFIG_BPF_JIT) += trampoline.o obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o +ifeq ($(CONFIG_MMU)$(CONFIG_64BIT),yy) +obj-$(CONFIG_BPF_SYSCALL) += arena.o +endif obj-$(CONFIG_BPF_JIT) += dispatcher.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c new file mode 100644 index 000000000000..86571e760dd6 --- /dev/null +++ b/kernel/bpf/arena.c @@ -0,0 +1,558 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */ +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <linux/btf_ids.h> +#include <linux/vmalloc.h> +#include <linux/pagemap.h> + +/* + * bpf_arena is a sparsely populated shared memory region between bpf program and + * user space process. + * + * For example on x86-64 the values could be: + * user_vm_start 7f7d26200000 // picked by mmap() + * kern_vm_start ffffc90001e69000 // picked by get_vm_area() + * For user space all pointers within the arena are normal 8-byte addresses. + * In this example 7f7d26200000 is the address of the first page (pgoff=0). + * The bpf program will access it as: kern_vm_start + lower_32bit_of_user_ptr + * (u32)7f7d26200000 -> 26200000 + * hence + * ffffc90001e69000 + 26200000 == ffffc90028069000 is "pgoff=0" within 4Gb + * kernel memory region. + * + * BPF JITs generate the following code to access arena: + * mov eax, eax // eax has lower 32-bit of user pointer + * mov word ptr [rax + r12 + off], bx + * where r12 == kern_vm_start and off is s16. + * Hence allocate 4Gb + GUARD_SZ/2 on each side. + * + * Initially kernel vm_area and user vma are not populated. + * User space can fault-in any address which will insert the page + * into kernel and user vma. + * bpf program can allocate a page via bpf_arena_alloc_pages() kfunc + * which will insert it into kernel vm_area. + * The later fault-in from user space will populate that page into user vma. + */ + +/* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */ +#define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8) +#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ) + +struct bpf_arena { + struct bpf_map map; + u64 user_vm_start; + u64 user_vm_end; + struct vm_struct *kern_vm; + struct maple_tree mt; + struct list_head vma_list; + struct mutex lock; +}; + +u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) +{ + return arena ? (u64) (long) arena->kern_vm->addr + GUARD_SZ / 2 : 0; +} + +u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) +{ + return arena ? arena->user_vm_start : 0; +} + +static long arena_map_peek_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long arena_map_push_elem(struct bpf_map *map, void *value, u64 flags) +{ + return -EOPNOTSUPP; +} + +static long arena_map_pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static long arena_map_delete_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static int arena_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -EOPNOTSUPP; +} + +static long compute_pgoff(struct bpf_arena *arena, long uaddr) +{ + return (u32)(uaddr - (u32)arena->user_vm_start) >> PAGE_SHIFT; +} + +static struct bpf_map *arena_map_alloc(union bpf_attr *attr) +{ + struct vm_struct *kern_vm; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_arena *arena; + u64 vm_range; + int err = -ENOMEM; + + if (attr->key_size || attr->value_size || attr->max_entries == 0 || + /* BPF_F_MMAPABLE must be set */ + !(attr->map_flags & BPF_F_MMAPABLE) || + /* No unsupported flags present */ + (attr->map_flags & ~(BPF_F_SEGV_ON_FAULT | BPF_F_MMAPABLE | BPF_F_NO_USER_CONV))) + return ERR_PTR(-EINVAL); + + if (attr->map_extra & ~PAGE_MASK) + /* If non-zero the map_extra is an expected user VMA start address */ + return ERR_PTR(-EINVAL); + + vm_range = (u64)attr->max_entries * PAGE_SIZE; + if (vm_range > (1ull << 32)) + return ERR_PTR(-E2BIG); + + if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32)) + /* user vma must not cross 32-bit boundary */ + return ERR_PTR(-ERANGE); + + kern_vm = get_vm_area(KERN_VM_SZ, VM_SPARSE | VM_USERMAP); + if (!kern_vm) + return ERR_PTR(-ENOMEM); + + arena = bpf_map_area_alloc(sizeof(*arena), numa_node); + if (!arena) + goto err; + + arena->kern_vm = kern_vm; + arena->user_vm_start = attr->map_extra; + if (arena->user_vm_start) + arena->user_vm_end = arena->user_vm_start + vm_range; + + INIT_LIST_HEAD(&arena->vma_list); + bpf_map_init_from_attr(&arena->map, attr); + mt_init_flags(&arena->mt, MT_FLAGS_ALLOC_RANGE); + mutex_init(&arena->lock); + + return &arena->map; +err: + free_vm_area(kern_vm); + return ERR_PTR(err); +} + +static int existing_page_cb(pte_t *ptep, unsigned long addr, void *data) +{ + struct page *page; + pte_t pte; + + pte = ptep_get(ptep); + if (!pte_present(pte)) /* sanity check */ + return 0; + page = pte_page(pte); + /* + * We do not update pte here: + * 1. Nobody should be accessing bpf_arena's range outside of a kernel bug + * 2. TLB flushing is batched or deferred. Even if we clear pte, + * the TLB entries can stick around and continue to permit access to + * the freed page. So it all relies on 1. + */ + __free_page(page); + return 0; +} + +static void arena_map_free(struct bpf_map *map) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + /* + * Check that user vma-s are not around when bpf map is freed. + * mmap() holds vm_file which holds bpf_map refcnt. + * munmap() must have happened on vma followed by arena_vm_close() + * which would clear arena->vma_list. + */ + if (WARN_ON_ONCE(!list_empty(&arena->vma_list))) + return; + + /* + * free_vm_area() calls remove_vm_area() that calls free_unmap_vmap_area(). + * It unmaps everything from vmalloc area and clears pgtables. + * Call apply_to_existing_page_range() first to find populated ptes and + * free those pages. + */ + apply_to_existing_page_range(&init_mm, bpf_arena_get_kern_vm_start(arena), + KERN_VM_SZ - GUARD_SZ, existing_page_cb, NULL); + free_vm_area(arena->kern_vm); + mtree_destroy(&arena->mt); + bpf_map_area_free(arena); +} + +static void *arena_map_lookup_elem(struct bpf_map *map, void *key) +{ + return ERR_PTR(-EINVAL); +} + +static long arena_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + return -EOPNOTSUPP; +} + +static int arena_map_check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, const struct btf_type *value_type) +{ + return 0; +} + +static u64 arena_map_mem_usage(const struct bpf_map *map) +{ + return 0; +} + +struct vma_list { + struct vm_area_struct *vma; + struct list_head head; +}; + +static int remember_vma(struct bpf_arena *arena, struct vm_area_struct *vma) +{ + struct vma_list *vml; + + vml = kmalloc(sizeof(*vml), GFP_KERNEL); + if (!vml) + return -ENOMEM; + vma->vm_private_data = vml; + vml->vma = vma; + list_add(&vml->head, &arena->vma_list); + return 0; +} + +static void arena_vm_close(struct vm_area_struct *vma) +{ + struct bpf_map *map = vma->vm_file->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + struct vma_list *vml; + + guard(mutex)(&arena->lock); + vml = vma->vm_private_data; + list_del(&vml->head); + vma->vm_private_data = NULL; + kfree(vml); +} + +#define MT_ENTRY ((void *)&arena_map_ops) /* unused. has to be valid pointer */ + +static vm_fault_t arena_vm_fault(struct vm_fault *vmf) +{ + struct bpf_map *map = vmf->vma->vm_file->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + struct page *page; + long kbase, kaddr; + int ret; + + kbase = bpf_arena_get_kern_vm_start(arena); + kaddr = kbase + (u32)(vmf->address & PAGE_MASK); + + guard(mutex)(&arena->lock); + page = vmalloc_to_page((void *)kaddr); + if (page) + /* already have a page vmap-ed */ + goto out; + + if (arena->map.map_flags & BPF_F_SEGV_ON_FAULT) + /* User space requested to segfault when page is not allocated by bpf prog */ + return VM_FAULT_SIGSEGV; + + ret = mtree_insert(&arena->mt, vmf->pgoff, MT_ENTRY, GFP_KERNEL); + if (ret) + return VM_FAULT_SIGSEGV; + + /* Account into memcg of the process that created bpf_arena */ + ret = bpf_map_alloc_pages(map, GFP_KERNEL | __GFP_ZERO, NUMA_NO_NODE, 1, &page); + if (ret) { + mtree_erase(&arena->mt, vmf->pgoff); + return VM_FAULT_SIGSEGV; + } + + ret = vm_area_map_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE, &page); + if (ret) { + mtree_erase(&arena->mt, vmf->pgoff); + __free_page(page); + return VM_FAULT_SIGSEGV; + } +out: + page_ref_add(page, 1); + vmf->page = page; + return 0; +} + +static const struct vm_operations_struct arena_vm_ops = { + .close = arena_vm_close, + .fault = arena_vm_fault, +}; + +static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct bpf_map *map = filp->private_data; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + long ret; + + if (pgoff) + return -EINVAL; + if (len > (1ull << 32)) + return -E2BIG; + + /* if user_vm_start was specified at arena creation time */ + if (arena->user_vm_start) { + if (len > arena->user_vm_end - arena->user_vm_start) + return -E2BIG; + if (len != arena->user_vm_end - arena->user_vm_start) + return -EINVAL; + if (addr != arena->user_vm_start) + return -EINVAL; + } + + ret = current->mm->get_unmapped_area(filp, addr, len * 2, 0, flags); + if (IS_ERR_VALUE(ret)) + return ret; + if ((ret >> 32) == ((ret + len - 1) >> 32)) + return ret; + if (WARN_ON_ONCE(arena->user_vm_start)) + /* checks at map creation time should prevent this */ + return -EFAULT; + return round_up(ret, 1ull << 32); +} + +static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + guard(mutex)(&arena->lock); + if (arena->user_vm_start && arena->user_vm_start != vma->vm_start) + /* + * If map_extra was not specified at arena creation time then + * 1st user process can do mmap(NULL, ...) to pick user_vm_start + * 2nd user process must pass the same addr to mmap(addr, MAP_FIXED..); + * or + * specify addr in map_extra and + * use the same addr later with mmap(addr, MAP_FIXED..); + */ + return -EBUSY; + + if (arena->user_vm_end && arena->user_vm_end != vma->vm_end) + /* all user processes must have the same size of mmap-ed region */ + return -EBUSY; + + /* Earlier checks should prevent this */ + if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff)) + return -EFAULT; + + if (remember_vma(arena, vma)) + return -ENOMEM; + + arena->user_vm_start = vma->vm_start; + arena->user_vm_end = vma->vm_end; + /* + * bpf_map_mmap() checks that it's being mmaped as VM_SHARED and + * clears VM_MAYEXEC. Set VM_DONTEXPAND as well to avoid + * potential change of user_vm_start. + */ + vm_flags_set(vma, VM_DONTEXPAND); + vma->vm_ops = &arena_vm_ops; + return 0; +} + +static int arena_map_direct_value_addr(const struct bpf_map *map, u64 *imm, u32 off) +{ + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if ((u64)off > arena->user_vm_end - arena->user_vm_start) + return -ERANGE; + *imm = (unsigned long)arena->user_vm_start; + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_arena_map_btf_ids, struct, bpf_arena) +const struct bpf_map_ops arena_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = arena_map_alloc, + .map_free = arena_map_free, + .map_direct_value_addr = arena_map_direct_value_addr, + .map_mmap = arena_map_mmap, + .map_get_unmapped_area = arena_get_unmapped_area, + .map_get_next_key = arena_map_get_next_key, + .map_push_elem = arena_map_push_elem, + .map_peek_elem = arena_map_peek_elem, + .map_pop_elem = arena_map_pop_elem, + .map_lookup_elem = arena_map_lookup_elem, + .map_update_elem = arena_map_update_elem, + .map_delete_elem = arena_map_delete_elem, + .map_check_btf = arena_map_check_btf, + .map_mem_usage = arena_map_mem_usage, + .map_btf_id = &bpf_arena_map_btf_ids[0], +}; + +static u64 clear_lo32(u64 val) +{ + return val & ~(u64)~0U; +} + +/* + * Allocate pages and vmap them into kernel vmalloc area. + * Later the pages will be mmaped into user space vma. + */ +static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt, int node_id) +{ + /* user_vm_end/start are fixed before bpf prog runs */ + long page_cnt_max = (arena->user_vm_end - arena->user_vm_start) >> PAGE_SHIFT; + u64 kern_vm_start = bpf_arena_get_kern_vm_start(arena); + struct page **pages; + long pgoff = 0; + u32 uaddr32; + int ret, i; + + if (page_cnt > page_cnt_max) + return 0; + + if (uaddr) { + if (uaddr & ~PAGE_MASK) + return 0; + pgoff = compute_pgoff(arena, uaddr); + if (pgoff + page_cnt > page_cnt_max) + /* requested address will be outside of user VMA */ + return 0; + } + + /* zeroing is needed, since alloc_pages_bulk_array() only fills in non-zero entries */ + pages = kvcalloc(page_cnt, sizeof(struct page *), GFP_KERNEL); + if (!pages) + return 0; + + guard(mutex)(&arena->lock); + + if (uaddr) + ret = mtree_insert_range(&arena->mt, pgoff, pgoff + page_cnt - 1, + MT_ENTRY, GFP_KERNEL); + else + ret = mtree_alloc_range(&arena->mt, &pgoff, MT_ENTRY, + page_cnt, 0, page_cnt_max - 1, GFP_KERNEL); + if (ret) + goto out_free_pages; + + ret = bpf_map_alloc_pages(&arena->map, GFP_KERNEL | __GFP_ZERO, + node_id, page_cnt, pages); + if (ret) + goto out; + + uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE); + /* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */ + ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32, + kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages); + if (ret) { + for (i = 0; i < page_cnt; i++) + __free_page(pages[i]); + goto out; + } + kvfree(pages); + return clear_lo32(arena->user_vm_start) + uaddr32; +out: + mtree_erase(&arena->mt, pgoff); +out_free_pages: + kvfree(pages); + return 0; +} + +/* + * If page is present in vmalloc area, unmap it from vmalloc area, + * unmap it from all user space vma-s, + * and free it. + */ +static void zap_pages(struct bpf_arena *arena, long uaddr, long page_cnt) +{ + struct vma_list *vml; + + list_for_each_entry(vml, &arena->vma_list, head) + zap_page_range_single(vml->vma, uaddr, + PAGE_SIZE * page_cnt, NULL); +} + +static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt) +{ + u64 full_uaddr, uaddr_end; + long kaddr, pgoff, i; + struct page *page; + + /* only aligned lower 32-bit are relevant */ + uaddr = (u32)uaddr; + uaddr &= PAGE_MASK; + full_uaddr = clear_lo32(arena->user_vm_start) + uaddr; + uaddr_end = min(arena->user_vm_end, full_uaddr + (page_cnt << PAGE_SHIFT)); + if (full_uaddr >= uaddr_end) + return; + + page_cnt = (uaddr_end - full_uaddr) >> PAGE_SHIFT; + + guard(mutex)(&arena->lock); + + pgoff = compute_pgoff(arena, uaddr); + /* clear range */ + mtree_store_range(&arena->mt, pgoff, pgoff + page_cnt - 1, NULL, GFP_KERNEL); + + if (page_cnt > 1) + /* bulk zap if multiple pages being freed */ + zap_pages(arena, full_uaddr, page_cnt); + + kaddr = bpf_arena_get_kern_vm_start(arena) + uaddr; + for (i = 0; i < page_cnt; i++, kaddr += PAGE_SIZE, full_uaddr += PAGE_SIZE) { + page = vmalloc_to_page((void *)kaddr); + if (!page) + continue; + if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */ + zap_pages(arena, full_uaddr, 1); + vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE); + __free_page(page); + } +} + +__bpf_kfunc_start_defs(); + +__bpf_kfunc void *bpf_arena_alloc_pages(void *p__map, void *addr__ign, u32 page_cnt, + int node_id, u64 flags) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA || flags || !page_cnt) + return NULL; + + return (void *)arena_alloc_pages(arena, (long)addr__ign, page_cnt, node_id); +} + +__bpf_kfunc void bpf_arena_free_pages(void *p__map, void *ptr__ign, u32 page_cnt) +{ + struct bpf_map *map = p__map; + struct bpf_arena *arena = container_of(map, struct bpf_arena, map); + + if (map->map_type != BPF_MAP_TYPE_ARENA || !page_cnt || !ptr__ign) + return; + arena_free_pages(arena, (long)ptr__ign, page_cnt); +} +__bpf_kfunc_end_defs(); + +BTF_KFUNCS_START(arena_kfuncs) +BTF_ID_FLAGS(func, bpf_arena_alloc_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +BTF_ID_FLAGS(func, bpf_arena_free_pages, KF_TRUSTED_ARGS | KF_SLEEPABLE) +BTF_KFUNCS_END(arena_kfuncs) + +static const struct btf_kfunc_id_set common_kfunc_set = { + .owner = THIS_MODULE, + .set = &arena_kfuncs, +}; + +static int __init kfunc_init(void) +{ + return register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC, &common_kfunc_set); +} +late_initcall(kfunc_init); diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0bdbbbeab155..13358675ff2e 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -82,7 +82,7 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; - bool bypass_spec_v1 = bpf_bypass_spec_v1(); + bool bypass_spec_v1 = bpf_bypass_spec_v1(NULL); u64 array_size, mask64; struct bpf_array *array; diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c index 0fae79164187..112581cf97e7 100644 --- a/kernel/bpf/bpf_iter.c +++ b/kernel/bpf/bpf_iter.c @@ -548,7 +548,7 @@ int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, return -ENOENT; /* Only allow sleepable program for resched-able iterator */ - if (prog->aux->sleepable && !bpf_iter_target_support_resched(tinfo)) + if (prog->sleepable && !bpf_iter_target_support_resched(tinfo)) return -EINVAL; link = kzalloc(sizeof(*link), GFP_USER | __GFP_NOWARN); @@ -697,7 +697,7 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx) struct bpf_run_ctx run_ctx, *old_run_ctx; int ret; - if (prog->aux->sleepable) { + if (prog->sleepable) { rcu_read_lock_trace(); migrate_disable(); might_fault(); diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 146824cc9689..bdea1a459153 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -414,47 +414,21 @@ void bpf_selem_unlink(struct bpf_local_storage_elem *selem, bool reuse_now) bpf_selem_unlink_storage(selem, reuse_now); } -/* If cacheit_lockit is false, this lookup function is lockless */ -struct bpf_local_storage_data * -bpf_local_storage_lookup(struct bpf_local_storage *local_storage, - struct bpf_local_storage_map *smap, - bool cacheit_lockit) +void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage, + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bpf_local_storage_data *sdata; - struct bpf_local_storage_elem *selem; - - /* Fast path (cache hit) */ - sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx], - bpf_rcu_lock_held()); - if (sdata && rcu_access_pointer(sdata->smap) == smap) - return sdata; - - /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &local_storage->list, snode, - rcu_read_lock_trace_held()) - if (rcu_access_pointer(SDATA(selem)->smap) == smap) - break; - - if (!selem) - return NULL; - - sdata = SDATA(selem); - if (cacheit_lockit) { - unsigned long flags; - - /* spinlock is needed to avoid racing with the - * parallel delete. Otherwise, publishing an already - * deleted sdata to the cache will become a use-after-free - * problem in the next bpf_local_storage_lookup(). - */ - raw_spin_lock_irqsave(&local_storage->lock, flags); - if (selem_linked_to_storage(selem)) - rcu_assign_pointer(local_storage->cache[smap->cache_idx], - sdata); - raw_spin_unlock_irqrestore(&local_storage->lock, flags); - } + unsigned long flags; - return sdata; + /* spinlock is needed to avoid racing with the + * parallel delete. Otherwise, publishing an already + * deleted sdata to the cache will become a use-after-free + * problem in the next bpf_local_storage_lookup(). + */ + raw_spin_lock_irqsave(&local_storage->lock, flags); + if (selem_linked_to_storage(selem)) + rcu_assign_pointer(local_storage->cache[smap->cache_idx], SDATA(selem)); + raw_spin_unlock_irqrestore(&local_storage->lock, flags); } static int check_flags(const struct bpf_local_storage_data *old_sdata, diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index e8e910395bf6..68240c3c6e7d 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -260,9 +260,15 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) BTF_SET_START(sleepable_lsm_hooks) BTF_ID(func, bpf_lsm_bpf) BTF_ID(func, bpf_lsm_bpf_map) -BTF_ID(func, bpf_lsm_bpf_map_alloc_security) -BTF_ID(func, bpf_lsm_bpf_map_free_security) +BTF_ID(func, bpf_lsm_bpf_map_create) +BTF_ID(func, bpf_lsm_bpf_map_free) BTF_ID(func, bpf_lsm_bpf_prog) +BTF_ID(func, bpf_lsm_bpf_prog_load) +BTF_ID(func, bpf_lsm_bpf_prog_free) +BTF_ID(func, bpf_lsm_bpf_token_create) +BTF_ID(func, bpf_lsm_bpf_token_free) +BTF_ID(func, bpf_lsm_bpf_token_cmd) +BTF_ID(func, bpf_lsm_bpf_token_capable) BTF_ID(func, bpf_lsm_bprm_check_security) BTF_ID(func, bpf_lsm_bprm_committed_creds) BTF_ID(func, bpf_lsm_bprm_committing_creds) @@ -276,10 +282,6 @@ BTF_ID(func, bpf_lsm_file_lock) BTF_ID(func, bpf_lsm_file_open) BTF_ID(func, bpf_lsm_file_receive) -#ifdef CONFIG_SECURITY_NETWORK -BTF_ID(func, bpf_lsm_inet_conn_established) -#endif /* CONFIG_SECURITY_NETWORK */ - BTF_ID(func, bpf_lsm_inode_create) BTF_ID(func, bpf_lsm_inode_free_security) BTF_ID(func, bpf_lsm_inode_getattr) @@ -330,6 +332,8 @@ BTF_ID(func, bpf_lsm_sb_umount) BTF_ID(func, bpf_lsm_settime) #ifdef CONFIG_SECURITY_NETWORK +BTF_ID(func, bpf_lsm_inet_conn_established) + BTF_ID(func, bpf_lsm_socket_accept) BTF_ID(func, bpf_lsm_socket_bind) BTF_ID(func, bpf_lsm_socket_connect) @@ -357,9 +361,8 @@ BTF_ID(func, bpf_lsm_userns_create) BTF_SET_END(sleepable_lsm_hooks) BTF_SET_START(untrusted_lsm_hooks) -BTF_ID(func, bpf_lsm_bpf_map_free_security) -BTF_ID(func, bpf_lsm_bpf_prog_alloc_security) -BTF_ID(func, bpf_lsm_bpf_prog_free_security) +BTF_ID(func, bpf_lsm_bpf_map_free) +BTF_ID(func, bpf_lsm_bpf_prog_free) BTF_ID(func, bpf_lsm_file_alloc_security) BTF_ID(func, bpf_lsm_file_free_security) #ifdef CONFIG_SECURITY_NETWORK diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 02068bd0e4d9..43356faaa057 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -13,26 +13,17 @@ #include <linux/btf_ids.h> #include <linux/rcupdate_wait.h> -enum bpf_struct_ops_state { - BPF_STRUCT_OPS_STATE_INIT, - BPF_STRUCT_OPS_STATE_INUSE, - BPF_STRUCT_OPS_STATE_TOBEFREE, - BPF_STRUCT_OPS_STATE_READY, -}; - -#define BPF_STRUCT_OPS_COMMON_VALUE \ - refcount_t refcnt; \ - enum bpf_struct_ops_state state - struct bpf_struct_ops_value { - BPF_STRUCT_OPS_COMMON_VALUE; + struct bpf_struct_ops_common_value common; char data[] ____cacheline_aligned_in_smp; }; +#define MAX_TRAMP_IMAGE_PAGES 8 + struct bpf_struct_ops_map { struct bpf_map map; struct rcu_head rcu; - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; /* protect map_update */ struct mutex lock; /* link has all the bpf_links that is populated @@ -40,12 +31,14 @@ struct bpf_struct_ops_map { * (in kvalue.data). */ struct bpf_link **links; - /* image is a page that has all the trampolines + u32 links_cnt; + u32 image_pages_cnt; + /* image_pages is an array of pages that has all the trampolines * that stores the func args before calling the bpf_prog. - * A PAGE_SIZE "image" is enough to store all trampoline for - * "links[]". */ - void *image; + void *image_pages[MAX_TRAMP_IMAGE_PAGES]; + /* The owner moduler's btf. */ + struct btf *btf; /* uvalue->data stores the kernel struct * (e.g. tcp_congestion_ops) that is more useful * to userspace than the kvalue. For example, @@ -70,35 +63,6 @@ static DEFINE_MUTEX(update_mutex); #define VALUE_PREFIX "bpf_struct_ops_" #define VALUE_PREFIX_LEN (sizeof(VALUE_PREFIX) - 1) -/* bpf_struct_ops_##_name (e.g. bpf_struct_ops_tcp_congestion_ops) is - * the map's value exposed to the userspace and its btf-type-id is - * stored at the map->btf_vmlinux_value_type_id. - * - */ -#define BPF_STRUCT_OPS_TYPE(_name) \ -extern struct bpf_struct_ops bpf_##_name; \ - \ -struct bpf_struct_ops_##_name { \ - BPF_STRUCT_OPS_COMMON_VALUE; \ - struct _name data ____cacheline_aligned_in_smp; \ -}; -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - -enum { -#define BPF_STRUCT_OPS_TYPE(_name) BPF_STRUCT_OPS_TYPE_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE - __NR_BPF_STRUCT_OPS_TYPE, -}; - -static struct bpf_struct_ops * const bpf_struct_ops[] = { -#define BPF_STRUCT_OPS_TYPE(_name) \ - [BPF_STRUCT_OPS_TYPE_##_name] = &bpf_##_name, -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE -}; - const struct bpf_verifier_ops bpf_struct_ops_verifier_ops = { }; @@ -108,138 +72,355 @@ const struct bpf_prog_ops bpf_struct_ops_prog_ops = { #endif }; -static const struct btf_type *module_type; +BTF_ID_LIST(st_ops_ids) +BTF_ID(struct, module) +BTF_ID(struct, bpf_struct_ops_common_value) + +enum { + IDX_MODULE_ID, + IDX_ST_OPS_COMMON_VALUE_ID, +}; + +extern struct btf *btf_vmlinux; -void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log) +static bool is_valid_value_type(struct btf *btf, s32 value_id, + const struct btf_type *type, + const char *value_name) { - s32 type_id, value_id, module_id; + const struct btf_type *common_value_type; const struct btf_member *member; - struct bpf_struct_ops *st_ops; - const struct btf_type *t; - char value_name[128]; - const char *mname; - u32 i, j; + const struct btf_type *vt, *mt; - /* Ensure BTF type is emitted for "struct bpf_struct_ops_##_name" */ -#define BPF_STRUCT_OPS_TYPE(_name) BTF_TYPE_EMIT(struct bpf_struct_ops_##_name); -#include "bpf_struct_ops_types.h" -#undef BPF_STRUCT_OPS_TYPE + vt = btf_type_by_id(btf, value_id); + if (btf_vlen(vt) != 2) { + pr_warn("The number of %s's members should be 2, but we get %d\n", + value_name, btf_vlen(vt)); + return false; + } + member = btf_type_member(vt); + mt = btf_type_by_id(btf, member->type); + common_value_type = btf_type_by_id(btf_vmlinux, + st_ops_ids[IDX_ST_OPS_COMMON_VALUE_ID]); + if (mt != common_value_type) { + pr_warn("The first member of %s should be bpf_struct_ops_common_value\n", + value_name); + return false; + } + member++; + mt = btf_type_by_id(btf, member->type); + if (mt != type) { + pr_warn("The second member of %s should be %s\n", + value_name, btf_name_by_offset(btf, type->name_off)); + return false; + } - module_id = btf_find_by_name_kind(btf, "module", BTF_KIND_STRUCT); - if (module_id < 0) { - pr_warn("Cannot find struct module in btf_vmlinux\n"); - return; + return true; +} + +static void *bpf_struct_ops_image_alloc(void) +{ + void *image; + int err; + + err = bpf_jit_charge_modmem(PAGE_SIZE); + if (err) + return ERR_PTR(err); + image = arch_alloc_bpf_trampoline(PAGE_SIZE); + if (!image) { + bpf_jit_uncharge_modmem(PAGE_SIZE); + return ERR_PTR(-ENOMEM); } - module_type = btf_type_by_id(btf, module_id); - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - st_ops = bpf_struct_ops[i]; + return image; +} - if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= - sizeof(value_name)) { - pr_warn("struct_ops name %s is too long\n", - st_ops->name); - continue; - } - sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); +void bpf_struct_ops_image_free(void *image) +{ + if (image) { + arch_free_bpf_trampoline(image, PAGE_SIZE); + bpf_jit_uncharge_modmem(PAGE_SIZE); + } +} + +#define MAYBE_NULL_SUFFIX "__nullable" +#define MAX_STUB_NAME 128 - value_id = btf_find_by_name_kind(btf, value_name, - BTF_KIND_STRUCT); - if (value_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - value_name); +/* Return the type info of a stub function, if it exists. + * + * The name of a stub function is made up of the name of the struct_ops and + * the name of the function pointer member, separated by "__". For example, + * if the struct_ops type is named "foo_ops" and the function pointer + * member is named "bar", the stub function name would be "foo_ops__bar". + */ +static const struct btf_type * +find_stub_func_proto(const struct btf *btf, const char *st_op_name, + const char *member_name) +{ + char stub_func_name[MAX_STUB_NAME]; + const struct btf_type *func_type; + s32 btf_id; + int cp; + + cp = snprintf(stub_func_name, MAX_STUB_NAME, "%s__%s", + st_op_name, member_name); + if (cp >= MAX_STUB_NAME) { + pr_warn("Stub function name too long\n"); + return NULL; + } + btf_id = btf_find_by_name_kind(btf, stub_func_name, BTF_KIND_FUNC); + if (btf_id < 0) + return NULL; + func_type = btf_type_by_id(btf, btf_id); + if (!func_type) + return NULL; + + return btf_type_by_id(btf, func_type->type); /* FUNC_PROTO */ +} + +/* Prepare argument info for every nullable argument of a member of a + * struct_ops type. + * + * Initialize a struct bpf_struct_ops_arg_info according to type info of + * the arguments of a stub function. (Check kCFI for more information about + * stub functions.) + * + * Each member in the struct_ops type has a struct bpf_struct_ops_arg_info + * to provide an array of struct bpf_ctx_arg_aux, which in turn provides + * the information that used by the verifier to check the arguments of the + * BPF struct_ops program assigned to the member. Here, we only care about + * the arguments that are marked as __nullable. + * + * The array of struct bpf_ctx_arg_aux is eventually assigned to + * prog->aux->ctx_arg_info of BPF struct_ops programs and passed to the + * verifier. (See check_struct_ops_btf_id()) + * + * arg_info->info will be the list of struct bpf_ctx_arg_aux if success. If + * fails, it will be kept untouched. + */ +static int prepare_arg_info(struct btf *btf, + const char *st_ops_name, + const char *member_name, + const struct btf_type *func_proto, + struct bpf_struct_ops_arg_info *arg_info) +{ + const struct btf_type *stub_func_proto, *pointed_type; + const struct btf_param *stub_args, *args; + struct bpf_ctx_arg_aux *info, *info_buf; + u32 nargs, arg_no, info_cnt = 0; + u32 arg_btf_id; + int offset; + + stub_func_proto = find_stub_func_proto(btf, st_ops_name, member_name); + if (!stub_func_proto) + return 0; + + /* Check if the number of arguments of the stub function is the same + * as the number of arguments of the function pointer. + */ + nargs = btf_type_vlen(func_proto); + if (nargs != btf_type_vlen(stub_func_proto)) { + pr_warn("the number of arguments of the stub function %s__%s does not match the number of arguments of the member %s of struct %s\n", + st_ops_name, member_name, member_name, st_ops_name); + return -EINVAL; + } + + if (!nargs) + return 0; + + args = btf_params(func_proto); + stub_args = btf_params(stub_func_proto); + + info_buf = kcalloc(nargs, sizeof(*info_buf), GFP_KERNEL); + if (!info_buf) + return -ENOMEM; + + /* Prepare info for every nullable argument */ + info = info_buf; + for (arg_no = 0; arg_no < nargs; arg_no++) { + /* Skip arguments that is not suffixed with + * "__nullable". + */ + if (!btf_param_match_suffix(btf, &stub_args[arg_no], + MAYBE_NULL_SUFFIX)) continue; + + /* Should be a pointer to struct */ + pointed_type = btf_type_resolve_ptr(btf, + args[arg_no].type, + &arg_btf_id); + if (!pointed_type || + !btf_type_is_struct(pointed_type)) { + pr_warn("stub function %s__%s has %s tagging to an unsupported type\n", + st_ops_name, member_name, MAYBE_NULL_SUFFIX); + goto err_out; } - type_id = btf_find_by_name_kind(btf, st_ops->name, - BTF_KIND_STRUCT); - if (type_id < 0) { - pr_warn("Cannot find struct %s in btf_vmlinux\n", - st_ops->name); - continue; + offset = btf_ctx_arg_offset(btf, func_proto, arg_no); + if (offset < 0) { + pr_warn("stub function %s__%s has an invalid trampoline ctx offset for arg#%u\n", + st_ops_name, member_name, arg_no); + goto err_out; } - t = btf_type_by_id(btf, type_id); - if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { - pr_warn("Cannot support #%u members in struct %s\n", - btf_type_vlen(t), st_ops->name); - continue; + + if (args[arg_no].type != stub_args[arg_no].type) { + pr_warn("arg#%u type in stub function %s__%s does not match with its original func_proto\n", + arg_no, st_ops_name, member_name); + goto err_out; } - for_each_member(j, t, member) { - const struct btf_type *func_proto; + /* Fill the information of the new argument */ + info->reg_type = + PTR_TRUSTED | PTR_TO_BTF_ID | PTR_MAYBE_NULL; + info->btf_id = arg_btf_id; + info->btf = btf; + info->offset = offset; - mname = btf_name_by_offset(btf, member->name_off); - if (!*mname) { - pr_warn("anon member in struct %s is not supported\n", - st_ops->name); - break; - } + info++; + info_cnt++; + } - if (__btf_member_bitfield_size(t, member)) { - pr_warn("bit field member %s in struct %s is not supported\n", - mname, st_ops->name); - break; - } + if (info_cnt) { + arg_info->info = info_buf; + arg_info->cnt = info_cnt; + } else { + kfree(info_buf); + } - func_proto = btf_type_resolve_func_ptr(btf, - member->type, - NULL); - if (func_proto && - btf_distill_func_proto(log, btf, - func_proto, mname, - &st_ops->func_models[j])) { - pr_warn("Error in parsing func ptr %s in struct %s\n", - mname, st_ops->name); - break; - } - } + return 0; - if (j == btf_type_vlen(t)) { - if (st_ops->init(btf)) { - pr_warn("Error in init bpf_struct_ops %s\n", - st_ops->name); - } else { - st_ops->type_id = type_id; - st_ops->type = t; - st_ops->value_id = value_id; - st_ops->value_type = btf_type_by_id(btf, - value_id); - } - } - } +err_out: + kfree(info_buf); + + return -EINVAL; } -extern struct btf *btf_vmlinux; +/* Clean up the arg_info in a struct bpf_struct_ops_desc. */ +void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc) +{ + struct bpf_struct_ops_arg_info *arg_info; + int i; -static const struct bpf_struct_ops * -bpf_struct_ops_find_value(u32 value_id) + arg_info = st_ops_desc->arg_info; + for (i = 0; i < btf_type_vlen(st_ops_desc->type); i++) + kfree(arg_info[i].info); + + kfree(arg_info); +} + +int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc, + struct btf *btf, + struct bpf_verifier_log *log) { - unsigned int i; + struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; + struct bpf_struct_ops_arg_info *arg_info; + const struct btf_member *member; + const struct btf_type *t; + s32 type_id, value_id; + char value_name[128]; + const char *mname; + int i, err; - if (!value_id || !btf_vmlinux) - return NULL; + if (strlen(st_ops->name) + VALUE_PREFIX_LEN >= + sizeof(value_name)) { + pr_warn("struct_ops name %s is too long\n", + st_ops->name); + return -EINVAL; + } + sprintf(value_name, "%s%s", VALUE_PREFIX, st_ops->name); - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->value_id == value_id) - return bpf_struct_ops[i]; + if (!st_ops->cfi_stubs) { + pr_warn("struct_ops for %s has no cfi_stubs\n", st_ops->name); + return -EINVAL; } - return NULL; -} + type_id = btf_find_by_name_kind(btf, st_ops->name, + BTF_KIND_STRUCT); + if (type_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + st_ops->name, btf_get_name(btf)); + return -EINVAL; + } + t = btf_type_by_id(btf, type_id); + if (btf_type_vlen(t) > BPF_STRUCT_OPS_MAX_NR_MEMBERS) { + pr_warn("Cannot support #%u members in struct %s\n", + btf_type_vlen(t), st_ops->name); + return -EINVAL; + } -const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id) -{ - unsigned int i; + value_id = btf_find_by_name_kind(btf, value_name, + BTF_KIND_STRUCT); + if (value_id < 0) { + pr_warn("Cannot find struct %s in %s\n", + value_name, btf_get_name(btf)); + return -EINVAL; + } + if (!is_valid_value_type(btf, value_id, t, value_name)) + return -EINVAL; - if (!type_id || !btf_vmlinux) - return NULL; + arg_info = kcalloc(btf_type_vlen(t), sizeof(*arg_info), + GFP_KERNEL); + if (!arg_info) + return -ENOMEM; + + st_ops_desc->arg_info = arg_info; + st_ops_desc->type = t; + st_ops_desc->type_id = type_id; + st_ops_desc->value_id = value_id; + st_ops_desc->value_type = btf_type_by_id(btf, value_id); + + for_each_member(i, t, member) { + const struct btf_type *func_proto; - for (i = 0; i < ARRAY_SIZE(bpf_struct_ops); i++) { - if (bpf_struct_ops[i]->type_id == type_id) - return bpf_struct_ops[i]; + mname = btf_name_by_offset(btf, member->name_off); + if (!*mname) { + pr_warn("anon member in struct %s is not supported\n", + st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + + if (__btf_member_bitfield_size(t, member)) { + pr_warn("bit field member %s in struct %s is not supported\n", + mname, st_ops->name); + err = -EOPNOTSUPP; + goto errout; + } + + func_proto = btf_type_resolve_func_ptr(btf, + member->type, + NULL); + if (!func_proto) + continue; + + if (btf_distill_func_proto(log, btf, + func_proto, mname, + &st_ops->func_models[i])) { + pr_warn("Error in parsing func ptr %s in struct %s\n", + mname, st_ops->name); + err = -EINVAL; + goto errout; + } + + err = prepare_arg_info(btf, st_ops->name, mname, + func_proto, + arg_info + i); + if (err) + goto errout; } - return NULL; + if (st_ops->init(btf)) { + pr_warn("Error in init bpf_struct_ops %s\n", + st_ops->name); + err = -EINVAL; + goto errout; + } + + return 0; + +errout: + bpf_struct_ops_desc_release(st_ops_desc); + + return err; } static int bpf_struct_ops_map_get_next_key(struct bpf_map *map, void *key, @@ -265,7 +446,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, kvalue = &st_map->kvalue; /* Pair with smp_store_release() during map_update */ - state = smp_load_acquire(&kvalue->state); + state = smp_load_acquire(&kvalue->common.state); if (state == BPF_STRUCT_OPS_STATE_INIT) { memset(value, 0, map->value_size); return 0; @@ -276,7 +457,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, */ uvalue = value; memcpy(uvalue, st_map->uvalue, map->value_size); - uvalue->state = state; + uvalue->common.state = state; /* This value offers the user space a general estimate of how * many sockets are still utilizing this struct_ops for TCP @@ -284,7 +465,7 @@ int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key, * should sufficiently meet our present goals. */ refcnt = atomic64_read(&map->refcnt) - atomic64_read(&map->usercnt); - refcount_set(&uvalue->refcnt, max_t(s64, refcnt, 0)); + refcount_set(&uvalue->common.refcnt, max_t(s64, refcnt, 0)); return 0; } @@ -296,10 +477,9 @@ static void *bpf_struct_ops_map_lookup_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) { - const struct btf_type *t = st_map->st_ops->type; u32 i; - for (i = 0; i < btf_type_vlen(t); i++) { + for (i = 0; i < st_map->links_cnt; i++) { if (st_map->links[i]) { bpf_link_put(st_map->links[i]); st_map->links[i] = NULL; @@ -307,7 +487,16 @@ static void bpf_struct_ops_map_put_progs(struct bpf_struct_ops_map *st_map) } } -static int check_zero_holes(const struct btf_type *t, void *data) +static void bpf_struct_ops_map_free_image(struct bpf_struct_ops_map *st_map) +{ + int i; + + for (i = 0; i < st_map->image_pages_cnt; i++) + bpf_struct_ops_image_free(st_map->image_pages[i]); + st_map->image_pages_cnt = 0; +} + +static int check_zero_holes(const struct btf *btf, const struct btf_type *t, void *data) { const struct btf_member *member; u32 i, moff, msize, prev_mend = 0; @@ -319,8 +508,8 @@ static int check_zero_holes(const struct btf_type *t, void *data) memchr_inv(data + prev_mend, 0, moff - prev_mend)) return -EINVAL; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(btf, member->type); + mtype = btf_resolve_size(btf, mtype, &msize); if (IS_ERR(mtype)) return PTR_ERR(mtype); prev_mend = moff + msize; @@ -352,9 +541,12 @@ const struct bpf_link_ops bpf_struct_ops_link_lops = { int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, struct bpf_tramp_link *link, const struct btf_func_model *model, - void *stub_func, void *image, void *image_end) + void *stub_func, + void **_image, u32 *_image_off, + bool allow_alloc) { - u32 flags = BPF_TRAMP_F_INDIRECT; + u32 image_off = *_image_off, flags = BPF_TRAMP_F_INDIRECT; + void *image = *_image; int size; tlinks[BPF_TRAMP_FENTRY].links[0] = link; @@ -364,27 +556,49 @@ int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks, flags |= BPF_TRAMP_F_RET_FENTRY_RET; size = arch_bpf_trampoline_size(model, flags, tlinks, NULL); - if (size < 0) - return size; - if (size > (unsigned long)image_end - (unsigned long)image) - return -E2BIG; - return arch_prepare_bpf_trampoline(NULL, image, image_end, + if (size <= 0) + return size ? : -EFAULT; + + /* Allocate image buffer if necessary */ + if (!image || size > PAGE_SIZE - image_off) { + if (!allow_alloc) + return -E2BIG; + + image = bpf_struct_ops_image_alloc(); + if (IS_ERR(image)) + return PTR_ERR(image); + image_off = 0; + } + + size = arch_prepare_bpf_trampoline(NULL, image + image_off, + image + PAGE_SIZE, model, flags, tlinks, stub_func); + if (size <= 0) { + if (image != *_image) + bpf_struct_ops_image_free(image); + return size ? : -EFAULT; + } + + *_image = image; + *_image_off = image_off + size; + return 0; } static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, void *value, u64 flags) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct bpf_struct_ops *st_ops = st_ops_desc->st_ops; struct bpf_struct_ops_value *uvalue, *kvalue; + const struct btf_type *module_type; const struct btf_member *member; - const struct btf_type *t = st_ops->type; + const struct btf_type *t = st_ops_desc->type; struct bpf_tramp_links *tlinks; void *udata, *kdata; int prog_fd, err; - void *image, *image_end; - u32 i; + u32 i, trampoline_start, image_off = 0; + void *cur_image = NULL, *image = NULL; if (flags) return -EINVAL; @@ -392,16 +606,16 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (*(u32 *)key != 0) return -E2BIG; - err = check_zero_holes(st_ops->value_type, value); + err = check_zero_holes(st_map->btf, st_ops_desc->value_type, value); if (err) return err; uvalue = value; - err = check_zero_holes(t, uvalue->data); + err = check_zero_holes(st_map->btf, t, uvalue->data); if (err) return err; - if (uvalue->state || refcount_read(&uvalue->refcnt)) + if (uvalue->common.state || refcount_read(&uvalue->common.refcnt)) return -EINVAL; tlinks = kcalloc(BPF_TRAMP_MAX, sizeof(*tlinks), GFP_KERNEL); @@ -413,7 +627,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, mutex_lock(&st_map->lock); - if (kvalue->state != BPF_STRUCT_OPS_STATE_INIT) { + if (kvalue->common.state != BPF_STRUCT_OPS_STATE_INIT) { err = -EBUSY; goto unlock; } @@ -422,9 +636,8 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, udata = &uvalue->data; kdata = &kvalue->data; - image = st_map->image; - image_end = st_map->image + PAGE_SIZE; + module_type = btf_type_by_id(btf_vmlinux, st_ops_ids[IDX_MODULE_ID]); for_each_member(i, t, member) { const struct btf_type *mtype, *ptype; struct bpf_prog *prog; @@ -432,7 +645,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, u32 moff; moff = __btf_member_bit_offset(t, member) / 8; - ptype = btf_type_resolve_ptr(btf_vmlinux, member->type, NULL); + ptype = btf_type_resolve_ptr(st_map->btf, member->type, NULL); if (ptype == module_type) { if (*(void **)(udata + moff)) goto reset_unlock; @@ -457,8 +670,8 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, if (!ptype || !btf_type_is_func_proto(ptype)) { u32 msize; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mtype = btf_resolve_size(btf_vmlinux, mtype, &msize); + mtype = btf_type_by_id(st_map->btf, member->type); + mtype = btf_resolve_size(st_map->btf, mtype, &msize); if (IS_ERR(mtype)) { err = PTR_ERR(mtype); goto reset_unlock; @@ -484,7 +697,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, } if (prog->type != BPF_PROG_TYPE_STRUCT_OPS || - prog->aux->attach_btf_id != st_ops->type_id || + prog->aux->attach_btf_id != st_ops_desc->type_id || prog->expected_attach_type != i) { bpf_prog_put(prog); err = -EINVAL; @@ -501,37 +714,47 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, &bpf_struct_ops_link_lops, prog); st_map->links[i] = &link->link; + trampoline_start = image_off; err = bpf_struct_ops_prepare_trampoline(tlinks, link, - &st_ops->func_models[i], - *(void **)(st_ops->cfi_stubs + moff), - image, image_end); + &st_ops->func_models[i], + *(void **)(st_ops->cfi_stubs + moff), + &image, &image_off, + st_map->image_pages_cnt < MAX_TRAMP_IMAGE_PAGES); + if (err) + goto reset_unlock; + + if (cur_image != image) { + st_map->image_pages[st_map->image_pages_cnt++] = image; + cur_image = image; + trampoline_start = 0; + } if (err < 0) goto reset_unlock; - *(void **)(kdata + moff) = image + cfi_get_offset(); - image += err; + *(void **)(kdata + moff) = image + trampoline_start + cfi_get_offset(); /* put prog_id to udata */ *(unsigned long *)(udata + moff) = prog->aux->id; } + if (st_ops->validate) { + err = st_ops->validate(kdata); + if (err) + goto reset_unlock; + } + for (i = 0; i < st_map->image_pages_cnt; i++) + arch_protect_bpf_trampoline(st_map->image_pages[i], PAGE_SIZE); + if (st_map->map.map_flags & BPF_F_LINK) { err = 0; - if (st_ops->validate) { - err = st_ops->validate(kdata); - if (err) - goto reset_unlock; - } - arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE); /* Let bpf_link handle registration & unregistration. * * Pair with smp_load_acquire() during lookup_elem(). */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_READY); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_READY); goto unlock; } - arch_protect_bpf_trampoline(st_map->image, PAGE_SIZE); err = st_ops->reg(kdata); if (likely(!err)) { /* This refcnt increment on the map here after @@ -545,7 +768,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * It ensures the above udata updates (e.g. prog->aux->id) * can be seen once BPF_STRUCT_OPS_STATE_INUSE is set. */ - smp_store_release(&kvalue->state, BPF_STRUCT_OPS_STATE_INUSE); + smp_store_release(&kvalue->common.state, BPF_STRUCT_OPS_STATE_INUSE); goto unlock; } @@ -554,9 +777,9 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key, * there was a race in registering the struct_ops (under the same name) to * a sub-system through different struct_ops's maps. */ - arch_unprotect_bpf_trampoline(st_map->image, PAGE_SIZE); reset_unlock: + bpf_struct_ops_map_free_image(st_map); bpf_struct_ops_map_put_progs(st_map); memset(uvalue, 0, map->value_size); memset(kvalue, 0, map->value_size); @@ -575,12 +798,12 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) if (st_map->map.map_flags & BPF_F_LINK) return -EOPNOTSUPP; - prev_state = cmpxchg(&st_map->kvalue.state, + prev_state = cmpxchg(&st_map->kvalue.common.state, BPF_STRUCT_OPS_STATE_INUSE, BPF_STRUCT_OPS_STATE_TOBEFREE); switch (prev_state) { case BPF_STRUCT_OPS_STATE_INUSE: - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(map); return 0; case BPF_STRUCT_OPS_STATE_TOBEFREE: @@ -597,6 +820,7 @@ static long bpf_struct_ops_map_delete_elem(struct bpf_map *map, void *key) static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; void *value; int err; @@ -606,7 +830,8 @@ static void bpf_struct_ops_map_seq_show_elem(struct bpf_map *map, void *key, err = bpf_struct_ops_map_sys_lookup_elem(map, key, value); if (!err) { - btf_type_seq_show(btf_vmlinux, map->btf_vmlinux_value_type_id, + btf_type_seq_show(st_map->btf, + map->btf_vmlinux_value_type_id, value, m); seq_puts(m, "\n"); } @@ -621,16 +846,22 @@ static void __bpf_struct_ops_map_free(struct bpf_map *map) if (st_map->links) bpf_struct_ops_map_put_progs(st_map); bpf_map_area_free(st_map->links); - if (st_map->image) { - arch_free_bpf_trampoline(st_map->image, PAGE_SIZE); - bpf_jit_uncharge_modmem(PAGE_SIZE); - } + bpf_struct_ops_map_free_image(st_map); bpf_map_area_free(st_map->uvalue); bpf_map_area_free(st_map); } static void bpf_struct_ops_map_free(struct bpf_map *map) { + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + /* st_ops->owner was acquired during map_alloc to implicitly holds + * the btf's refcnt. The acquire was only done when btf_is_module() + * st_map->btf cannot be NULL here. + */ + if (btf_is_module(st_map->btf)) + module_put(st_map->st_ops_desc->st_ops->owner); + /* The struct_ops's function may switch to another struct_ops. * * For example, bpf_tcp_cc_x->init() may switch to @@ -654,29 +885,61 @@ static void bpf_struct_ops_map_free(struct bpf_map *map) static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) { if (attr->key_size != sizeof(unsigned int) || attr->max_entries != 1 || - (attr->map_flags & ~BPF_F_LINK) || !attr->btf_vmlinux_value_type_id) + (attr->map_flags & ~(BPF_F_LINK | BPF_F_VTYPE_BTF_OBJ_FD)) || + !attr->btf_vmlinux_value_type_id) return -EINVAL; return 0; } static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) { - const struct bpf_struct_ops *st_ops; + const struct bpf_struct_ops_desc *st_ops_desc; size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; + struct module *mod = NULL; struct bpf_map *map; + struct btf *btf; int ret; - st_ops = bpf_struct_ops_find_value(attr->btf_vmlinux_value_type_id); - if (!st_ops) - return ERR_PTR(-ENOTSUPP); + if (attr->map_flags & BPF_F_VTYPE_BTF_OBJ_FD) { + /* The map holds btf for its whole life time. */ + btf = btf_get_by_fd(attr->value_type_btf_obj_fd); + if (IS_ERR(btf)) + return ERR_CAST(btf); + if (!btf_is_module(btf)) { + btf_put(btf); + return ERR_PTR(-EINVAL); + } + + mod = btf_try_get_module(btf); + /* mod holds a refcnt to btf. We don't need an extra refcnt + * here. + */ + btf_put(btf); + if (!mod) + return ERR_PTR(-EINVAL); + } else { + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return ERR_CAST(btf); + if (!btf) + return ERR_PTR(-ENOTSUPP); + } + + st_ops_desc = bpf_struct_ops_find_value(btf, attr->btf_vmlinux_value_type_id); + if (!st_ops_desc) { + ret = -ENOTSUPP; + goto errout; + } - vt = st_ops->value_type; - if (attr->value_size != vt->size) - return ERR_PTR(-EINVAL); + vt = st_ops_desc->value_type; + if (attr->value_size != vt->size) { + ret = -EINVAL; + goto errout; + } - t = st_ops->type; + t = st_ops_desc->type; st_map_size = sizeof(*st_map) + /* kvalue stores the @@ -685,48 +948,43 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) (vt->size - sizeof(struct bpf_struct_ops_value)); st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); - if (!st_map) - return ERR_PTR(-ENOMEM); + if (!st_map) { + ret = -ENOMEM; + goto errout; + } - st_map->st_ops = st_ops; + st_map->st_ops_desc = st_ops_desc; map = &st_map->map; - ret = bpf_jit_charge_modmem(PAGE_SIZE); - if (ret) { - __bpf_struct_ops_map_free(map); - return ERR_PTR(ret); - } - - st_map->image = arch_alloc_bpf_trampoline(PAGE_SIZE); - if (!st_map->image) { - /* __bpf_struct_ops_map_free() uses st_map->image as flag - * for "charged or not". In this case, we need to unchange - * here. - */ - bpf_jit_uncharge_modmem(PAGE_SIZE); - __bpf_struct_ops_map_free(map); - return ERR_PTR(-ENOMEM); - } st_map->uvalue = bpf_map_area_alloc(vt->size, NUMA_NO_NODE); + st_map->links_cnt = btf_type_vlen(t); st_map->links = - bpf_map_area_alloc(btf_type_vlen(t) * sizeof(struct bpf_links *), + bpf_map_area_alloc(st_map->links_cnt * sizeof(struct bpf_links *), NUMA_NO_NODE); if (!st_map->uvalue || !st_map->links) { - __bpf_struct_ops_map_free(map); - return ERR_PTR(-ENOMEM); + ret = -ENOMEM; + goto errout_free; } + st_map->btf = btf; mutex_init(&st_map->lock); bpf_map_init_from_attr(map, attr); return map; + +errout_free: + __bpf_struct_ops_map_free(map); +errout: + module_put(mod); + + return ERR_PTR(ret); } static u64 bpf_struct_ops_map_mem_usage(const struct bpf_map *map) { struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; - const struct bpf_struct_ops *st_ops = st_map->st_ops; - const struct btf_type *vt = st_ops->value_type; + const struct bpf_struct_ops_desc *st_ops_desc = st_map->st_ops_desc; + const struct btf_type *vt = st_ops_desc->value_type; u64 usage; usage = sizeof(*st_map) + @@ -785,7 +1043,7 @@ static bool bpf_struct_ops_valid_to_reg(struct bpf_map *map) return map->map_type == BPF_MAP_TYPE_STRUCT_OPS && map->map_flags & BPF_F_LINK && /* Pair with smp_store_release() during map_update */ - smp_load_acquire(&st_map->kvalue.state) == BPF_STRUCT_OPS_STATE_READY; + smp_load_acquire(&st_map->kvalue.common.state) == BPF_STRUCT_OPS_STATE_READY; } static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) @@ -800,7 +1058,7 @@ static void bpf_struct_ops_map_link_dealloc(struct bpf_link *link) /* st_link->map can be NULL if * bpf_struct_ops_link_create() fails to register. */ - st_map->st_ops->unreg(&st_map->kvalue.data); + st_map->st_ops_desc->st_ops->unreg(&st_map->kvalue.data); bpf_map_put(&st_map->map); } kfree(st_link); @@ -847,7 +1105,7 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map if (!bpf_struct_ops_valid_to_reg(new_map)) return -EINVAL; - if (!st_map->st_ops->update) + if (!st_map->st_ops_desc->st_ops->update) return -EOPNOTSUPP; mutex_lock(&update_mutex); @@ -860,12 +1118,12 @@ static int bpf_struct_ops_map_link_update(struct bpf_link *link, struct bpf_map old_st_map = container_of(old_map, struct bpf_struct_ops_map, map); /* The new and old struct_ops must be the same type. */ - if (st_map->st_ops != old_st_map->st_ops) { + if (st_map->st_ops_desc != old_st_map->st_ops_desc) { err = -EINVAL; goto err_out; } - err = st_map->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->update(st_map->kvalue.data, old_st_map->kvalue.data); if (err) goto err_out; @@ -916,7 +1174,7 @@ int bpf_struct_ops_link_create(union bpf_attr *attr) if (err) goto err_out; - err = st_map->st_ops->reg(st_map->kvalue.data); + err = st_map->st_ops_desc->st_ops->reg(st_map->kvalue.data); if (err) { bpf_link_cleanup(&link_primer); link = NULL; @@ -931,3 +1189,10 @@ err_out: kfree(link); return err; } + +void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map) +{ + struct bpf_struct_ops_map *st_map = (struct bpf_struct_ops_map *)map; + + info->btf_vmlinux_id = btf_obj_id(st_map->btf); +} diff --git a/kernel/bpf/bpf_struct_ops_types.h b/kernel/bpf/bpf_struct_ops_types.h deleted file mode 100644 index 5678a9ddf817..000000000000 --- a/kernel/bpf/bpf_struct_ops_types.h +++ /dev/null @@ -1,12 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* internal file - do not include directly */ - -#ifdef CONFIG_BPF_JIT -#ifdef CONFIG_NET -BPF_STRUCT_OPS_TYPE(bpf_dummy_ops) -#endif -#ifdef CONFIG_INET -#include <net/tcp.h> -BPF_STRUCT_OPS_TYPE(tcp_congestion_ops) -#endif -#endif diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 596471189176..90c4a32d89ff 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -19,6 +19,7 @@ #include <linux/bpf_verifier.h> #include <linux/btf.h> #include <linux/btf_ids.h> +#include <linux/bpf.h> #include <linux/bpf_lsm.h> #include <linux/skmsg.h> #include <linux/perf_event.h> @@ -241,6 +242,12 @@ struct btf_id_dtor_kfunc_tab { struct btf_id_dtor_kfunc dtors[]; }; +struct btf_struct_ops_tab { + u32 cnt; + u32 capacity; + struct bpf_struct_ops_desc ops[]; +}; + struct btf { void *data; struct btf_type **types; @@ -258,6 +265,7 @@ struct btf { struct btf_kfunc_set_tab *kfunc_set_tab; struct btf_id_dtor_kfunc_tab *dtor_kfunc_tab; struct btf_struct_metas *struct_meta_tab; + struct btf_struct_ops_tab *struct_ops_tab; /* split BTF support */ struct btf *base_btf; @@ -801,9 +809,23 @@ static bool btf_name_valid_identifier(const struct btf *btf, u32 offset) return __btf_name_valid(btf, offset); } +/* Allow any printable character in DATASEC names */ static bool btf_name_valid_section(const struct btf *btf, u32 offset) { - return __btf_name_valid(btf, offset); + /* offset must be valid */ + const char *src = btf_str_by_offset(btf, offset); + const char *src_limit; + + /* set a limit on identifier length */ + src_limit = src + KSYM_NAME_LEN; + src++; + while (*src && src < src_limit) { + if (!isprint(*src)) + return false; + src++; + } + + return !*src; } static const char *__btf_name_by_offset(const struct btf *btf, u32 offset) @@ -1688,11 +1710,27 @@ static void btf_free_struct_meta_tab(struct btf *btf) btf->struct_meta_tab = NULL; } +static void btf_free_struct_ops_tab(struct btf *btf) +{ + struct btf_struct_ops_tab *tab = btf->struct_ops_tab; + u32 i; + + if (!tab) + return; + + for (i = 0; i < tab->cnt; i++) + bpf_struct_ops_desc_release(&tab->ops[i]); + + kfree(tab); + btf->struct_ops_tab = NULL; +} + static void btf_free(struct btf *btf) { btf_free_struct_meta_tab(btf); btf_free_dtor_kfunc_tab(btf); btf_free_kfunc_set_tab(btf); + btf_free_struct_ops_tab(btf); kvfree(btf->types); kvfree(btf->resolved_sizes); kvfree(btf->resolved_ids); @@ -1707,6 +1745,11 @@ static void btf_free_rcu(struct rcu_head *rcu) btf_free(btf); } +const char *btf_get_name(const struct btf *btf) +{ + return btf->name; +} + void btf_get(struct btf *btf) { refcount_inc(&btf->refcnt); @@ -3310,30 +3353,48 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, return BTF_FIELD_FOUND; } -const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, - int comp_idx, const char *tag_key) +int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key, int last_id) { - const char *value = NULL; - int i; + int len = strlen(tag_key); + int i, n; - for (i = 1; i < btf_nr_types(btf); i++) { + for (i = last_id + 1, n = btf_nr_types(btf); i < n; i++) { const struct btf_type *t = btf_type_by_id(btf, i); - int len = strlen(tag_key); if (!btf_type_is_decl_tag(t)) continue; - if (pt != btf_type_by_id(btf, t->type) || - btf_type_decl_tag(t)->component_idx != comp_idx) + if (pt != btf_type_by_id(btf, t->type)) + continue; + if (btf_type_decl_tag(t)->component_idx != comp_idx) continue; if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) continue; - /* Prevent duplicate entries for same type */ - if (value) - return ERR_PTR(-EEXIST); - value = __btf_name_by_offset(btf, t->name_off) + len; + return i; } - if (!value) - return ERR_PTR(-ENOENT); + return -ENOENT; +} + +const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key) +{ + const char *value = NULL; + const struct btf_type *t; + int len, id; + + id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, 0); + if (id < 0) + return ERR_PTR(id); + + t = btf_type_by_id(btf, id); + len = strlen(tag_key); + value = __btf_name_by_offset(btf, t->name_off) + len; + + /* Prevent duplicate entries for same type */ + id = btf_find_next_decl_tag(btf, pt, comp_idx, tag_key, id); + if (id >= 0) + return ERR_PTR(-EEXIST); + return value; } @@ -5647,15 +5708,29 @@ static int find_kern_ctx_type_id(enum bpf_prog_type prog_type) return ctx_type->type; } -const struct btf_type * -btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, - const struct btf_type *t, enum bpf_prog_type prog_type, - int arg) +bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, + const struct btf_type *t, enum bpf_prog_type prog_type, + int arg) { const struct btf_type *ctx_type; const char *tname, *ctx_tname; t = btf_type_by_id(btf, t->type); + + /* KPROBE programs allow bpf_user_pt_regs_t typedef, which we need to + * check before we skip all the typedef below. + */ + if (prog_type == BPF_PROG_TYPE_KPROBE) { + while (btf_type_is_modifier(t) && !btf_type_is_typedef(t)) + t = btf_type_by_id(btf, t->type); + + if (btf_type_is_typedef(t)) { + tname = btf_name_by_offset(btf, t->name_off); + if (tname && strcmp(tname, "bpf_user_pt_regs_t") == 0) + return true; + } + } + while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_struct(t)) { @@ -5664,27 +5739,30 @@ btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf, * is not supported yet. * BPF_PROG_TYPE_RAW_TRACEPOINT is fine. */ - return NULL; + return false; } tname = btf_name_by_offset(btf, t->name_off); if (!tname) { bpf_log(log, "arg#%d struct doesn't have a name\n", arg); - return NULL; + return false; } ctx_type = find_canonical_prog_ctx_type(prog_type); if (!ctx_type) { bpf_log(log, "btf_vmlinux is malformed\n"); /* should not happen */ - return NULL; + return false; } again: ctx_tname = btf_name_by_offset(btf_vmlinux, ctx_type->name_off); if (!ctx_tname) { /* should not happen */ bpf_log(log, "Please fix kernel include/linux/bpf_types.h\n"); - return NULL; + return false; } + /* program types without named context types work only with arg:ctx tag */ + if (ctx_tname[0] == '\0') + return false; /* only compare that prog's ctx type name is the same as * kernel expects. No need to compare field by field. * It's ok for bpf prog to do: @@ -5693,20 +5771,20 @@ again: * { // no fields of skb are ever used } */ if (strcmp(ctx_tname, "__sk_buff") == 0 && strcmp(tname, "sk_buff") == 0) - return ctx_type; + return true; if (strcmp(ctx_tname, "xdp_md") == 0 && strcmp(tname, "xdp_buff") == 0) - return ctx_type; + return true; if (strcmp(ctx_tname, tname)) { /* bpf_user_pt_regs_t is a typedef, so resolve it to * underlying struct and check name again */ if (!btf_type_is_modifier(ctx_type)) - return NULL; + return false; while (btf_type_is_modifier(ctx_type)) ctx_type = btf_type_by_id(btf_vmlinux, ctx_type->type); goto again; } - return ctx_type; + return true; } /* forward declarations for arch-specific underlying types of @@ -5858,7 +5936,7 @@ static int btf_translate_to_vmlinux(struct bpf_verifier_log *log, enum bpf_prog_type prog_type, int arg) { - if (!btf_get_prog_ctx_type(log, btf, t, prog_type, arg)) + if (!btf_is_prog_ctx_type(log, btf, t, prog_type, arg)) return -ENOENT; return find_kern_ctx_type_id(prog_type); } @@ -5933,8 +6011,6 @@ struct btf *btf_parse_vmlinux(void) /* btf_parse_vmlinux() runs under bpf_verifier_lock */ bpf_ctx_convert.t = btf_type_by_id(btf, bpf_ctx_convert_btf_id[0]); - bpf_struct_ops_init(btf, log); - refcount_set(&btf->refcnt, 1); err = btf_alloc_id(btf); @@ -6092,6 +6168,26 @@ static bool prog_args_trusted(const struct bpf_prog *prog) } } +int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto, + u32 arg_no) +{ + const struct btf_param *args; + const struct btf_type *t; + int off = 0, i; + u32 sz; + + args = btf_params(func_proto); + for (i = 0; i < arg_no; i++) { + t = btf_type_by_id(btf, args[i].type); + t = btf_resolve_size(btf, t, &sz); + if (IS_ERR(t)) + return PTR_ERR(t); + off += roundup(sz, 8); + } + + return off; +} + bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) @@ -6228,7 +6324,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } info->reg_type = ctx_arg_info->reg_type; - info->btf = btf_vmlinux; + info->btf = ctx_arg_info->btf ? : btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; return true; } @@ -6284,6 +6380,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, __btf_name_by_offset(btf, t->name_off)); return true; } +EXPORT_SYMBOL_GPL(btf_ctx_access); enum bpf_struct_walk_result { /* < 0 error */ @@ -6946,6 +7043,81 @@ static bool btf_is_dynptr_ptr(const struct btf *btf, const struct btf_type *t) return false; } +struct bpf_cand_cache { + const char *name; + u32 name_len; + u16 kind; + u16 cnt; + struct { + const struct btf *btf; + u32 id; + } cands[]; +}; + +static DEFINE_MUTEX(cand_cache_mutex); + +static struct bpf_cand_cache * +bpf_core_find_cands(struct bpf_core_ctx *ctx, u32 local_type_id); + +static int btf_get_ptr_to_btf_id(struct bpf_verifier_log *log, int arg_idx, + const struct btf *btf, const struct btf_type *t) +{ + struct bpf_cand_cache *cc; + struct bpf_core_ctx ctx = { + .btf = btf, + .log = log, + }; + u32 kern_type_id, type_id; + int err = 0; + + /* skip PTR and modifiers */ + type_id = t->type; + t = btf_type_by_id(btf, t->type); + while (btf_type_is_modifier(t)) { + type_id = t->type; + t = btf_type_by_id(btf, t->type); + } + + mutex_lock(&cand_cache_mutex); + cc = bpf_core_find_cands(&ctx, type_id); + if (IS_ERR(cc)) { + err = PTR_ERR(cc); + bpf_log(log, "arg#%d reference type('%s %s') candidate matching error: %d\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), + err); + goto cand_cache_unlock; + } + if (cc->cnt != 1) { + bpf_log(log, "arg#%d reference type('%s %s') %s\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off), + cc->cnt == 0 ? "has no matches" : "is ambiguous"); + err = cc->cnt == 0 ? -ENOENT : -ESRCH; + goto cand_cache_unlock; + } + if (btf_is_module(cc->cands[0].btf)) { + bpf_log(log, "arg#%d reference type('%s %s') points to kernel module type (unsupported)\n", + arg_idx, btf_type_str(t), __btf_name_by_offset(btf, t->name_off)); + err = -EOPNOTSUPP; + goto cand_cache_unlock; + } + kern_type_id = cc->cands[0].id; + +cand_cache_unlock: + mutex_unlock(&cand_cache_mutex); + if (err) + return err; + + return kern_type_id; +} + +enum btf_arg_tag { + ARG_TAG_CTX = BIT_ULL(0), + ARG_TAG_NONNULL = BIT_ULL(1), + ARG_TAG_TRUSTED = BIT_ULL(2), + ARG_TAG_NULLABLE = BIT_ULL(3), + ARG_TAG_ARENA = BIT_ULL(4), +}; + /* Process BTF of a function to produce high-level expectation of function * arguments (like ARG_PTR_TO_CTX, or ARG_PTR_TO_MEM, etc). This information * is cached in subprog info for reuse. @@ -7009,6 +7181,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) args = (const struct btf_param *)(t + 1); nargs = btf_type_vlen(t); if (nargs > MAX_BPF_FUNC_REG_ARGS) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() with %d > %d args. Buggy compiler.\n", tname, nargs, MAX_BPF_FUNC_REG_ARGS); return -EINVAL; @@ -7018,6 +7192,8 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); if (!btf_type_is_int(t) && !btf_is_any_enum(t)) { + if (!is_global) + return -EINVAL; bpf_log(log, "Global function %s() doesn't return scalar. Only those are supported.\n", tname); @@ -7027,92 +7203,134 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog) * Only PTR_TO_CTX and SCALAR are supported atm. */ for (i = 0; i < nargs; i++) { - bool is_nonnull = false; - const char *tag; + u32 tags = 0; + int id = 0; - t = btf_type_by_id(btf, args[i].type); - - tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); - if (IS_ERR(tag) && PTR_ERR(tag) == -ENOENT) { - tag = NULL; - } else if (IS_ERR(tag)) { - bpf_log(log, "arg#%d type's tag fetching failure: %ld\n", i, PTR_ERR(tag)); - return PTR_ERR(tag); - } /* 'arg:<tag>' decl_tag takes precedence over derivation of * register type from BTF type itself */ - if (tag) { + while ((id = btf_find_next_decl_tag(btf, fn_t, i, "arg:", id)) > 0) { + const struct btf_type *tag_t = btf_type_by_id(btf, id); + const char *tag = __btf_name_by_offset(btf, tag_t->name_off) + 4; + /* disallow arg tags in static subprogs */ if (!is_global) { bpf_log(log, "arg#%d type tag is not supported in static functions\n", i); return -EOPNOTSUPP; } + if (strcmp(tag, "ctx") == 0) { - sub->args[i].arg_type = ARG_PTR_TO_CTX; - continue; + tags |= ARG_TAG_CTX; + } else if (strcmp(tag, "trusted") == 0) { + tags |= ARG_TAG_TRUSTED; + } else if (strcmp(tag, "nonnull") == 0) { + tags |= ARG_TAG_NONNULL; + } else if (strcmp(tag, "nullable") == 0) { + tags |= ARG_TAG_NULLABLE; + } else if (strcmp(tag, "arena") == 0) { + tags |= ARG_TAG_ARENA; + } else { + bpf_log(log, "arg#%d has unsupported set of tags\n", i); + return -EOPNOTSUPP; } - if (strcmp(tag, "nonnull") == 0) - is_nonnull = true; + } + if (id != -ENOENT) { + bpf_log(log, "arg#%d type tag fetching failure: %d\n", i, id); + return id; } + t = btf_type_by_id(btf, args[i].type); while (btf_type_is_modifier(t)) t = btf_type_by_id(btf, t->type); - if (btf_type_is_int(t) || btf_is_any_enum(t)) { - sub->args[i].arg_type = ARG_ANYTHING; - continue; - } - if (btf_type_is_ptr(t) && btf_get_prog_ctx_type(log, btf, t, prog_type, i)) { + if (!btf_type_is_ptr(t)) + goto skip_pointer; + + if ((tags & ARG_TAG_CTX) || btf_is_prog_ctx_type(log, btf, t, prog_type, i)) { + if (tags & ~ARG_TAG_CTX) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + if ((tags & ARG_TAG_CTX) && + btf_validate_prog_ctx_type(log, btf, t, i, prog_type, + prog->expected_attach_type)) + return -EINVAL; sub->args[i].arg_type = ARG_PTR_TO_CTX; continue; } - if (btf_type_is_ptr(t) && btf_is_dynptr_ptr(btf, t)) { + if (btf_is_dynptr_ptr(btf, t)) { + if (tags) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } sub->args[i].arg_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY; continue; } - if (is_global && btf_type_is_ptr(t)) { + if (tags & ARG_TAG_TRUSTED) { + int kern_type_id; + + if (tags & ARG_TAG_NONNULL) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + + kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t); + if (kern_type_id < 0) + return kern_type_id; + + sub->args[i].arg_type = ARG_PTR_TO_BTF_ID | PTR_TRUSTED; + if (tags & ARG_TAG_NULLABLE) + sub->args[i].arg_type |= PTR_MAYBE_NULL; + sub->args[i].btf_id = kern_type_id; + continue; + } + if (tags & ARG_TAG_ARENA) { + if (tags & ~ARG_TAG_ARENA) { + bpf_log(log, "arg#%d arena cannot be combined with any other tags\n", i); + return -EINVAL; + } + sub->args[i].arg_type = ARG_PTR_TO_ARENA; + continue; + } + if (is_global) { /* generic user data pointer */ u32 mem_size; + if (tags & ARG_TAG_NULLABLE) { + bpf_log(log, "arg#%d has invalid combination of tags\n", i); + return -EINVAL; + } + t = btf_type_skip_modifiers(btf, t->type, NULL); ref_t = btf_resolve_size(btf, t, &mem_size); if (IS_ERR(ref_t)) { - bpf_log(log, - "arg#%d reference type('%s %s') size cannot be determined: %ld\n", - i, btf_type_str(t), btf_name_by_offset(btf, t->name_off), + bpf_log(log, "arg#%d reference type('%s %s') size cannot be determined: %ld\n", + i, btf_type_str(t), btf_name_by_offset(btf, t->name_off), PTR_ERR(ref_t)); return -EINVAL; } - sub->args[i].arg_type = is_nonnull ? ARG_PTR_TO_MEM : ARG_PTR_TO_MEM_OR_NULL; + sub->args[i].arg_type = ARG_PTR_TO_MEM | PTR_MAYBE_NULL; + if (tags & ARG_TAG_NONNULL) + sub->args[i].arg_type &= ~PTR_MAYBE_NULL; sub->args[i].mem_size = mem_size; continue; } - if (is_nonnull) { - bpf_log(log, "arg#%d marked as non-null, but is not a pointer type\n", i); + +skip_pointer: + if (tags) { + bpf_log(log, "arg#%d has pointer tag, but is not a pointer type\n", i); return -EINVAL; } + if (btf_type_is_int(t) || btf_is_any_enum(t)) { + sub->args[i].arg_type = ARG_ANYTHING; + continue; + } + if (!is_global) + return -EINVAL; bpf_log(log, "Arg#%d type %s in %s() is not supported yet.\n", i, btf_type_str(t), tname); return -EINVAL; } - for (i = 0; i < nargs; i++) { - const char *tag; - - if (sub->args[i].arg_type != ARG_PTR_TO_CTX) - continue; - - /* check if arg has "arg:ctx" tag */ - t = btf_type_by_id(btf, args[i].type); - tag = btf_find_decl_tag_value(btf, fn_t, i, "arg:"); - if (IS_ERR_OR_NULL(tag) || strcmp(tag, "ctx") != 0) - continue; - - if (btf_validate_prog_ctx_type(log, btf, t, i, prog_type, - prog->expected_attach_type)) - return -EINVAL; - } - sub->arg_cnt = nargs; sub->args_cached = true; @@ -7589,6 +7807,17 @@ static struct btf *btf_get_module_btf(const struct module *module) return btf; } +static int check_btf_kconfigs(const struct module *module, const char *feature) +{ + if (!module && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { + pr_err("missing vmlinux BTF, cannot register %s\n", feature); + return -ENOENT; + } + if (module && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) + pr_warn("missing module BTF, cannot register %s\n", feature); + return 0; +} + BPF_CALL_4(bpf_btf_find_by_name_kind, char *, name, int, name_sz, u32, kind, int, flags) { struct btf *btf = NULL; @@ -7949,15 +8178,8 @@ static int __register_btf_kfunc_id_set(enum btf_kfunc_hook hook, int ret, i; btf = btf_get_module_btf(kset->owner); - if (!btf) { - if (!kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { - pr_err("missing vmlinux BTF, cannot register kfuncs\n"); - return -ENOENT; - } - if (kset->owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) - pr_warn("missing module BTF, cannot register kfuncs\n"); - return 0; - } + if (!btf) + return check_btf_kconfigs(kset->owner, "kfunc"); if (IS_ERR(btf)) return PTR_ERR(btf); @@ -7981,6 +8203,14 @@ int register_btf_kfunc_id_set(enum bpf_prog_type prog_type, { enum btf_kfunc_hook hook; + /* All kfuncs need to be tagged as such in BTF. + * WARN() for initcall registrations that do not check errors. + */ + if (!(kset->set->flags & BTF_SET8_KFUNCS)) { + WARN_ON(!kset->owner); + return -EINVAL; + } + hook = bpf_prog_type_to_kfunc_hook(prog_type); return __register_btf_kfunc_id_set(hook, kset); } @@ -8057,17 +8287,8 @@ int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_c int ret; btf = btf_get_module_btf(owner); - if (!btf) { - if (!owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF)) { - pr_err("missing vmlinux BTF, cannot register dtor kfuncs\n"); - return -ENOENT; - } - if (owner && IS_ENABLED(CONFIG_DEBUG_INFO_BTF_MODULES)) { - pr_err("missing module BTF, cannot register dtor kfuncs\n"); - return -ENOENT; - } - return 0; - } + if (!btf) + return check_btf_kconfigs(owner, "dtor kfuncs"); if (IS_ERR(btf)) return PTR_ERR(btf); @@ -8182,17 +8403,6 @@ size_t bpf_core_essential_name_len(const char *name) return n; } -struct bpf_cand_cache { - const char *name; - u32 name_len; - u16 kind; - u16 cnt; - struct { - const struct btf *btf; - u32 id; - } cands[]; -}; - static void bpf_free_cands(struct bpf_cand_cache *cands) { if (!cands->cnt) @@ -8213,8 +8423,6 @@ static struct bpf_cand_cache *vmlinux_cand_cache[VMLINUX_CAND_CACHE_SIZE]; #define MODULE_CAND_CACHE_SIZE 31 static struct bpf_cand_cache *module_cand_cache[MODULE_CAND_CACHE_SIZE]; -static DEFINE_MUTEX(cand_cache_mutex); - static void __print_cand_cache(struct bpf_verifier_log *log, struct bpf_cand_cache **cache, int cache_size) @@ -8645,3 +8853,141 @@ bool btf_type_ids_nocast_alias(struct bpf_verifier_log *log, return !strncmp(reg_name, arg_name, cmp_len); } + +#ifdef CONFIG_BPF_JIT +static int +btf_add_struct_ops(struct btf *btf, struct bpf_struct_ops *st_ops, + struct bpf_verifier_log *log) +{ + struct btf_struct_ops_tab *tab, *new_tab; + int i, err; + + tab = btf->struct_ops_tab; + if (!tab) { + tab = kzalloc(offsetof(struct btf_struct_ops_tab, ops[4]), + GFP_KERNEL); + if (!tab) + return -ENOMEM; + tab->capacity = 4; + btf->struct_ops_tab = tab; + } + + for (i = 0; i < tab->cnt; i++) + if (tab->ops[i].st_ops == st_ops) + return -EEXIST; + + if (tab->cnt == tab->capacity) { + new_tab = krealloc(tab, + offsetof(struct btf_struct_ops_tab, + ops[tab->capacity * 2]), + GFP_KERNEL); + if (!new_tab) + return -ENOMEM; + tab = new_tab; + tab->capacity *= 2; + btf->struct_ops_tab = tab; + } + + tab->ops[btf->struct_ops_tab->cnt].st_ops = st_ops; + + err = bpf_struct_ops_desc_init(&tab->ops[btf->struct_ops_tab->cnt], btf, log); + if (err) + return err; + + btf->struct_ops_tab->cnt++; + + return 0; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find_value(struct btf *btf, u32 value_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!value_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].value_id == value_id) + return &st_ops_list[i]; + } + + return NULL; +} + +const struct bpf_struct_ops_desc * +bpf_struct_ops_find(struct btf *btf, u32 type_id) +{ + const struct bpf_struct_ops_desc *st_ops_list; + unsigned int i; + u32 cnt; + + if (!type_id) + return NULL; + if (!btf->struct_ops_tab) + return NULL; + + cnt = btf->struct_ops_tab->cnt; + st_ops_list = btf->struct_ops_tab->ops; + for (i = 0; i < cnt; i++) { + if (st_ops_list[i].type_id == type_id) + return &st_ops_list[i]; + } + + return NULL; +} + +int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops) +{ + struct bpf_verifier_log *log; + struct btf *btf; + int err = 0; + + btf = btf_get_module_btf(st_ops->owner); + if (!btf) + return check_btf_kconfigs(st_ops->owner, "struct_ops"); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + log = kzalloc(sizeof(*log), GFP_KERNEL | __GFP_NOWARN); + if (!log) { + err = -ENOMEM; + goto errout; + } + + log->level = BPF_LOG_KERNEL; + + err = btf_add_struct_ops(btf, st_ops, log); + +errout: + kfree(log); + btf_put(btf); + + return err; +} +EXPORT_SYMBOL_GPL(__register_bpf_struct_ops); +#endif + +bool btf_param_match_suffix(const struct btf *btf, + const struct btf_param *arg, + const char *suffix) +{ + int suffix_len = strlen(suffix), len; + const char *param_name; + + /* In the future, this can be ported to use BTF tagging */ + param_name = btf_name_by_offset(btf, arg->name_off); + if (str_is_empty(param_name)) + return false; + len = strlen(param_name); + if (len <= suffix_len) + return false; + param_name += len - suffix_len; + return !strncmp(param_name, suffix, suffix_len); +} diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 491d20038cbe..82243cb6c54d 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -1358,15 +1358,12 @@ int __cgroup_bpf_run_filter_skb(struct sock *sk, struct sk_buff *skb, enum cgroup_bpf_attach_type atype) { - unsigned int offset = skb->data - skb_network_header(skb); + unsigned int offset = -skb_network_offset(skb); struct sock *save_sk; void *saved_data_end; struct cgroup *cgrp; int ret; - if (!sk || !sk_fullsock(sk)) - return 0; - if (sk->sk_family != AF_INET && sk->sk_family != AF_INET6) return 0; @@ -1630,7 +1627,7 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2191,7 +2188,7 @@ sysctl_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2348,7 +2345,7 @@ cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_event_output_data_proto; default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ea6843be2616..696bc55de8e8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -88,13 +88,18 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns return NULL; } +/* tell bpf programs that include vmlinux.h kernel's PAGE_SIZE */ +enum page_size_enum { + __PAGE_SIZE = PAGE_SIZE +}; + struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { gfp_t gfp_flags = bpf_memcg_flags(GFP_KERNEL | __GFP_ZERO | gfp_extra_flags); struct bpf_prog_aux *aux; struct bpf_prog *fp; - size = round_up(size, PAGE_SIZE); + size = round_up(size, __PAGE_SIZE); fp = __vmalloc(size, gfp_flags); if (fp == NULL) return NULL; @@ -682,7 +687,7 @@ static bool bpf_prog_kallsyms_candidate(const struct bpf_prog *fp) void bpf_prog_kallsyms_add(struct bpf_prog *fp) { if (!bpf_prog_kallsyms_candidate(fp) || - !bpf_capable()) + !bpf_token_capable(fp->aux->token, CAP_BPF)) return; bpf_prog_ksym_set_addr(fp); @@ -888,7 +893,12 @@ static LIST_HEAD(pack_list); * CONFIG_MMU=n. Use PAGE_SIZE in these cases. */ #ifdef PMD_SIZE -#define BPF_PROG_PACK_SIZE (PMD_SIZE * num_possible_nodes()) +/* PMD_SIZE is really big for some archs. It doesn't make sense to + * reserve too much memory in one allocation. Hardcode BPF_PROG_PACK_SIZE to + * 2MiB * num_possible_nodes(). On most architectures PMD_SIZE will be + * greater than or equal to 2MB. + */ +#define BPF_PROG_PACK_SIZE (SZ_2M * num_possible_nodes()) #else #define BPF_PROG_PACK_SIZE PAGE_SIZE #endif @@ -1675,6 +1685,7 @@ bool bpf_opcode_in_insntable(u8 code) [BPF_LD | BPF_IND | BPF_B] = true, [BPF_LD | BPF_IND | BPF_H] = true, [BPF_LD | BPF_IND | BPF_W] = true, + [BPF_JMP | BPF_JCOND] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL @@ -2695,7 +2706,7 @@ void __bpf_free_used_maps(struct bpf_prog_aux *aux, bool sleepable; u32 i; - sleepable = aux->sleepable; + sleepable = aux->prog->sleepable; for (i = 0; i < len; i++) { map = used_maps[i]; if (map->ops->map_poke_untrack) @@ -2779,6 +2790,7 @@ void bpf_prog_free(struct bpf_prog *fp) if (aux->dst_prog) bpf_prog_put(aux->dst_prog); + bpf_token_put(aux->token); INIT_WORK(&aux->work, bpf_prog_free_deferred); schedule_work(&aux->work); } @@ -2925,6 +2937,21 @@ bool __weak bpf_jit_supports_far_kfunc_call(void) return false; } +bool __weak bpf_jit_supports_arena(void) +{ + return false; +} + +/* Return TRUE if the JIT backend satisfies the following two conditions: + * 1) JIT backend supports atomic_xchg() on pointer-sized words. + * 2) Under the specific arch, the implementation of xchg() is the same + * as atomic_xchg() on pointer-sized words. + */ +bool __weak bpf_jit_supports_ptr_xchg(void) +{ + return false; +} + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ @@ -2959,6 +2986,17 @@ void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, { } +/* for configs without MMU or 32-bit */ +__weak const struct bpf_map_ops arena_map_ops; +__weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena) +{ + return 0; +} +__weak u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena) +{ + return 0; +} + #ifdef CONFIG_BPF_SYSCALL static int __init bpf_global_ma_init(void) { diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8a0bb80fe48a..9ee8da477465 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -24,6 +24,7 @@ #include <linux/filter.h> #include <linux/ptr_ring.h> #include <net/xdp.h> +#include <net/hotdata.h> #include <linux/sched.h> #include <linux/workqueue.h> @@ -178,7 +179,7 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu, void **frames, int n, struct xdp_cpumap_stats *stats) { - struct xdp_rxq_info rxq; + struct xdp_rxq_info rxq = {}; struct xdp_buff xdp; int i, nframes = 0; @@ -326,7 +327,8 @@ static int cpu_map_kthread_run(void *data) /* Support running another XDP prog on this CPU */ nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list); if (nframes) { - m = kmem_cache_alloc_bulk(skbuff_cache, gfp, nframes, skbs); + m = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, + gfp, nframes, skbs); if (unlikely(m == 0)) { for (i = 0; i < nframes; i++) skbs[i] = NULL; /* effect: xdp_return_frame */ diff --git a/kernel/bpf/cpumask.c b/kernel/bpf/cpumask.c index 2e73533a3811..dad0fb1c8e87 100644 --- a/kernel/bpf/cpumask.c +++ b/kernel/bpf/cpumask.c @@ -424,7 +424,7 @@ __bpf_kfunc u32 bpf_cpumask_weight(const struct cpumask *cpumask) __bpf_kfunc_end_defs(); -BTF_SET8_START(cpumask_kfunc_btf_ids) +BTF_KFUNCS_START(cpumask_kfunc_btf_ids) BTF_ID_FLAGS(func, bpf_cpumask_create, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_cpumask_release, KF_RELEASE) BTF_ID_FLAGS(func, bpf_cpumask_acquire, KF_ACQUIRE | KF_TRUSTED_ARGS) @@ -450,7 +450,7 @@ BTF_ID_FLAGS(func, bpf_cpumask_copy, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_any_and_distribute, KF_RCU) BTF_ID_FLAGS(func, bpf_cpumask_weight, KF_RCU) -BTF_SET8_END(cpumask_kfunc_btf_ids) +BTF_KFUNCS_END(cpumask_kfunc_btf_ids) static const struct btf_kfunc_id_set cpumask_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index a936c704d4e7..4e2cdbb5629f 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -130,13 +130,14 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) bpf_map_init_from_attr(&dtab->map, attr); if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { - dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); - - if (!dtab->n_buckets) /* Overflow check */ + /* hash table size must be power of 2; roundup_pow_of_two() can + * overflow into UB on 32-bit arches, so check that first + */ + if (dtab->map.max_entries > 1UL << 31) return -EINVAL; - } - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) diff --git a/kernel/bpf/disasm.c b/kernel/bpf/disasm.c index 49940c26a227..bd2e2dd04740 100644 --- a/kernel/bpf/disasm.c +++ b/kernel/bpf/disasm.c @@ -166,6 +166,12 @@ static bool is_movsx(const struct bpf_insn *insn) (insn->off == 8 || insn->off == 16 || insn->off == 32); } +static bool is_addr_space_cast(const struct bpf_insn *insn) +{ + return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && + insn->off == BPF_ADDR_SPACE_CAST; +} + void print_bpf_insn(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, bool allow_ptr_leaks) @@ -184,6 +190,10 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); + } else if (is_addr_space_cast(insn)) { + verbose(cbs->private_data, "(%02x) r%d = addr_space_cast(r%d, %d, %d)\n", + insn->code, insn->dst_reg, + insn->src_reg, ((u32)insn->imm) >> 16, (u16)insn->imm); } else if (BPF_SRC(insn->code) == BPF_X) { verbose(cbs->private_data, "(%02x) %c%d %s %s%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', @@ -322,6 +332,10 @@ void print_bpf_insn(const struct bpf_insn_cbs *cbs, } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(cbs->private_data, "(%02x) goto pc%+d\n", insn->code, insn->off); + } else if (insn->code == (BPF_JMP | BPF_JCOND) && + insn->src_reg == BPF_MAY_GOTO) { + verbose(cbs->private_data, "(%02x) may_goto pc%+d\n", + insn->code, insn->off); } else if (insn->code == (BPF_JMP32 | BPF_JA)) { verbose(cbs->private_data, "(%02x) gotol pc%+d\n", insn->code, insn->imm); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 03a6a2500b6a..3a088a5349bc 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -499,7 +499,13 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) num_possible_cpus()); } - /* hash table size must be power of 2 */ + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + err = -E2BIG; + if (htab->map.max_entries > 1UL << 31) + goto free_htab; + htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct htab_elem) + @@ -509,10 +515,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) else htab->elem_size += round_up(htab->map.value_size, 8); - err = -E2BIG; - /* prevent zero size kmalloc and check for u32 overflow */ - if (htab->n_buckets == 0 || - htab->n_buckets > U32_MAX / sizeof(struct bucket)) + /* check for u32 overflow */ + if (htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; err = bpf_map_init_elem_count(&htab->map); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index be72824f32b2..a89587859571 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -334,7 +334,7 @@ static inline void __bpf_spin_lock_irqsave(struct bpf_spin_lock *lock) __this_cpu_write(irqsave_flags, flags); } -notrace BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_lock, struct bpf_spin_lock *, lock) { __bpf_spin_lock_irqsave(lock); return 0; @@ -357,7 +357,7 @@ static inline void __bpf_spin_unlock_irqrestore(struct bpf_spin_lock *lock) local_irq_restore(flags); } -notrace BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) +NOTRACE_BPF_CALL_1(bpf_spin_unlock, struct bpf_spin_lock *, lock) { __bpf_spin_unlock_irqrestore(lock); return 0; @@ -1101,6 +1101,7 @@ struct bpf_hrtimer { struct bpf_prog *prog; void __rcu *callback_fn; void *value; + struct rcu_head rcu; }; /* the actual struct hidden inside uapi struct bpf_timer */ @@ -1332,6 +1333,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) if (in_nmi()) return -EOPNOTSUPP; + rcu_read_lock(); __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t) { @@ -1353,6 +1355,7 @@ out: * if it was running. */ ret = ret ?: hrtimer_cancel(&t->timer); + rcu_read_unlock(); return ret; } @@ -1407,13 +1410,14 @@ out: */ if (this_cpu_read(hrtimer_running) != t) hrtimer_cancel(&t->timer); - kfree(t); + kfree_rcu(t, rcu); } BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) { unsigned long *kptr = map_value; + /* This helper may be inlined by verifier. */ return xchg(kptr, (unsigned long)ptr); } @@ -1679,7 +1683,7 @@ const struct bpf_func_proto bpf_probe_read_kernel_str_proto __weak; const struct bpf_func_proto bpf_task_pt_regs_proto __weak; const struct bpf_func_proto * -bpf_base_func_proto(enum bpf_func_id func_id) +bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_map_lookup_elem: @@ -1730,7 +1734,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!bpf_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_BPF)) return NULL; switch (func_id) { @@ -1788,7 +1792,7 @@ bpf_base_func_proto(enum bpf_func_id func_id) break; } - if (!perfmon_capable()) + if (!bpf_token_capable(prog->aux->token, CAP_PERFMON)) return NULL; switch (func_id) { @@ -2483,9 +2487,9 @@ __bpf_kfunc void *bpf_cast_to_kern_ctx(void *obj) return obj; } -__bpf_kfunc void *bpf_rdonly_cast(void *obj__ign, u32 btf_id__k) +__bpf_kfunc void *bpf_rdonly_cast(const void *obj__ign, u32 btf_id__k) { - return obj__ign; + return (void *)obj__ign; } __bpf_kfunc void bpf_rcu_read_lock(void) @@ -2543,7 +2547,7 @@ __bpf_kfunc void bpf_throw(u64 cookie) __bpf_kfunc_end_defs(); -BTF_SET8_START(generic_btf_ids) +BTF_KFUNCS_START(generic_btf_ids) #ifdef CONFIG_KEXEC_CORE BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) #endif @@ -2572,7 +2576,7 @@ BTF_ID_FLAGS(func, bpf_task_get_cgroup1, KF_ACQUIRE | KF_RCU | KF_RET_NULL) #endif BTF_ID_FLAGS(func, bpf_task_from_pid, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_throw) -BTF_SET8_END(generic_btf_ids) +BTF_KFUNCS_END(generic_btf_ids) static const struct btf_kfunc_id_set generic_kfunc_set = { .owner = THIS_MODULE, @@ -2588,7 +2592,7 @@ BTF_ID(struct, cgroup) BTF_ID(func, bpf_cgroup_release_dtor) #endif -BTF_SET8_START(common_btf_ids) +BTF_KFUNCS_START(common_btf_ids) BTF_ID_FLAGS(func, bpf_cast_to_kern_ctx) BTF_ID_FLAGS(func, bpf_rdonly_cast) BTF_ID_FLAGS(func, bpf_rcu_read_lock) @@ -2617,7 +2621,7 @@ BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) BTF_ID_FLAGS(func, bpf_dynptr_size) BTF_ID_FLAGS(func, bpf_dynptr_clone) -BTF_SET8_END(common_btf_ids) +BTF_KFUNCS_END(common_btf_ids) static const struct btf_kfunc_id_set common_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index 41e0a55c35f5..af5d2ffadd70 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -20,6 +20,7 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <linux/kstrtox.h> #include "preload/bpf_preload.h" enum bpf_type { @@ -98,9 +99,9 @@ static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static const struct inode_operations bpf_link_iops = { }; -static struct inode *bpf_get_inode(struct super_block *sb, - const struct inode *dir, - umode_t mode) +struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) { struct inode *inode; @@ -594,6 +595,136 @@ struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type typ } EXPORT_SYMBOL(bpf_prog_get_type_path); +struct bpffs_btf_enums { + const struct btf *btf; + const struct btf_type *cmd_t; + const struct btf_type *map_t; + const struct btf_type *prog_t; + const struct btf_type *attach_t; +}; + +static int find_bpffs_btf_enums(struct bpffs_btf_enums *info) +{ + const struct btf *btf; + const struct btf_type *t; + const char *name; + int i, n; + + memset(info, 0, sizeof(*info)); + + btf = bpf_get_btf_vmlinux(); + if (IS_ERR(btf)) + return PTR_ERR(btf); + if (!btf) + return -ENOENT; + + info->btf = btf; + + for (i = 1, n = btf_nr_types(btf); i < n; i++) { + t = btf_type_by_id(btf, i); + if (!btf_type_is_enum(t)) + continue; + + name = btf_name_by_offset(btf, t->name_off); + if (!name) + continue; + + if (strcmp(name, "bpf_cmd") == 0) + info->cmd_t = t; + else if (strcmp(name, "bpf_map_type") == 0) + info->map_t = t; + else if (strcmp(name, "bpf_prog_type") == 0) + info->prog_t = t; + else if (strcmp(name, "bpf_attach_type") == 0) + info->attach_t = t; + else + continue; + + if (info->cmd_t && info->map_t && info->prog_t && info->attach_t) + return 0; + } + + return -ESRCH; +} + +static bool find_btf_enum_const(const struct btf *btf, const struct btf_type *enum_t, + const char *prefix, const char *str, int *value) +{ + const struct btf_enum *e; + const char *name; + int i, n, pfx_len = strlen(prefix); + + *value = 0; + + if (!btf || !enum_t) + return false; + + for (i = 0, n = btf_vlen(enum_t); i < n; i++) { + e = &btf_enum(enum_t)[i]; + + name = btf_name_by_offset(btf, e->name_off); + if (!name || strncasecmp(name, prefix, pfx_len) != 0) + continue; + + /* match symbolic name case insensitive and ignoring prefix */ + if (strcasecmp(name + pfx_len, str) == 0) { + *value = e->val; + return true; + } + } + + return false; +} + +static void seq_print_delegate_opts(struct seq_file *m, + const char *opt_name, + const struct btf *btf, + const struct btf_type *enum_t, + const char *prefix, + u64 delegate_msk, u64 any_msk) +{ + const struct btf_enum *e; + bool first = true; + const char *name; + u64 msk; + int i, n, pfx_len = strlen(prefix); + + delegate_msk &= any_msk; /* clear unknown bits */ + + if (delegate_msk == 0) + return; + + seq_printf(m, ",%s", opt_name); + if (delegate_msk == any_msk) { + seq_printf(m, "=any"); + return; + } + + if (btf && enum_t) { + for (i = 0, n = btf_vlen(enum_t); i < n; i++) { + e = &btf_enum(enum_t)[i]; + name = btf_name_by_offset(btf, e->name_off); + if (!name || strncasecmp(name, prefix, pfx_len) != 0) + continue; + msk = 1ULL << e->val; + if (delegate_msk & msk) { + /* emit lower-case name without prefix */ + seq_printf(m, "%c", first ? '=' : ':'); + name += pfx_len; + while (*name) { + seq_printf(m, "%c", tolower(*name)); + name++; + } + + delegate_msk &= ~msk; + first = false; + } + } + } + if (delegate_msk) + seq_printf(m, "%c0x%llx", first ? '=' : ':', delegate_msk); +} + /* * Display the mount options in /proc/mounts. */ @@ -601,6 +732,8 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) { struct inode *inode = d_inode(root); umode_t mode = inode->i_mode & S_IALLUGO & ~S_ISVTX; + struct bpf_mount_opts *opts = root->d_sb->s_fs_info; + u64 mask; if (!uid_eq(inode->i_uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", @@ -610,6 +743,35 @@ static int bpf_show_options(struct seq_file *m, struct dentry *root) from_kgid_munged(&init_user_ns, inode->i_gid)); if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); + + if (opts->delegate_cmds || opts->delegate_maps || + opts->delegate_progs || opts->delegate_attachs) { + struct bpffs_btf_enums info; + + /* ignore errors, fallback to hex */ + (void)find_bpffs_btf_enums(&info); + + mask = (1ULL << __MAX_BPF_CMD) - 1; + seq_print_delegate_opts(m, "delegate_cmds", + info.btf, info.cmd_t, "BPF_", + opts->delegate_cmds, mask); + + mask = (1ULL << __MAX_BPF_MAP_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_maps", + info.btf, info.map_t, "BPF_MAP_TYPE_", + opts->delegate_maps, mask); + + mask = (1ULL << __MAX_BPF_PROG_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_progs", + info.btf, info.prog_t, "BPF_PROG_TYPE_", + opts->delegate_progs, mask); + + mask = (1ULL << __MAX_BPF_ATTACH_TYPE) - 1; + seq_print_delegate_opts(m, "delegate_attachs", + info.btf, info.attach_t, "BPF_", + opts->delegate_attachs, mask); + } + return 0; } @@ -624,7 +786,7 @@ static void bpf_free_inode(struct inode *inode) free_inode_nonrcu(inode); } -static const struct super_operations bpf_super_ops = { +const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, @@ -635,28 +797,30 @@ enum { OPT_UID, OPT_GID, OPT_MODE, + OPT_DELEGATE_CMDS, + OPT_DELEGATE_MAPS, + OPT_DELEGATE_PROGS, + OPT_DELEGATE_ATTACHS, }; static const struct fs_parameter_spec bpf_fs_parameters[] = { fsparam_u32 ("uid", OPT_UID), fsparam_u32 ("gid", OPT_GID), fsparam_u32oct ("mode", OPT_MODE), + fsparam_string ("delegate_cmds", OPT_DELEGATE_CMDS), + fsparam_string ("delegate_maps", OPT_DELEGATE_MAPS), + fsparam_string ("delegate_progs", OPT_DELEGATE_PROGS), + fsparam_string ("delegate_attachs", OPT_DELEGATE_ATTACHS), {} }; -struct bpf_mount_opts { - kuid_t uid; - kgid_t gid; - umode_t mode; -}; - static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = fc->s_fs_info; struct fs_parse_result result; kuid_t uid; kgid_t gid; - int opt; + int opt, err; opt = fs_parse(fc, bpf_fs_parameters, param, &result); if (opt < 0) { @@ -708,6 +872,67 @@ static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; + case OPT_DELEGATE_CMDS: + case OPT_DELEGATE_MAPS: + case OPT_DELEGATE_PROGS: + case OPT_DELEGATE_ATTACHS: { + struct bpffs_btf_enums info; + const struct btf_type *enum_t; + const char *enum_pfx; + u64 *delegate_msk, msk = 0; + char *p; + int val; + + /* ignore errors, fallback to hex */ + (void)find_bpffs_btf_enums(&info); + + switch (opt) { + case OPT_DELEGATE_CMDS: + delegate_msk = &opts->delegate_cmds; + enum_t = info.cmd_t; + enum_pfx = "BPF_"; + break; + case OPT_DELEGATE_MAPS: + delegate_msk = &opts->delegate_maps; + enum_t = info.map_t; + enum_pfx = "BPF_MAP_TYPE_"; + break; + case OPT_DELEGATE_PROGS: + delegate_msk = &opts->delegate_progs; + enum_t = info.prog_t; + enum_pfx = "BPF_PROG_TYPE_"; + break; + case OPT_DELEGATE_ATTACHS: + delegate_msk = &opts->delegate_attachs; + enum_t = info.attach_t; + enum_pfx = "BPF_"; + break; + default: + return -EINVAL; + } + + while ((p = strsep(¶m->string, ":"))) { + if (strcmp(p, "any") == 0) { + msk |= ~0ULL; + } else if (find_btf_enum_const(info.btf, enum_t, enum_pfx, p, &val)) { + msk |= 1ULL << val; + } else { + err = kstrtou64(p, 0, &msk); + if (err) + return err; + } + } + + /* Setting delegation mount options requires privileges */ + if (msk && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + *delegate_msk |= msk; + break; + } + default: + /* ignore unknown mount options */ + break; } return 0; @@ -784,10 +1009,14 @@ out: static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; - struct bpf_mount_opts *opts = fc->fs_private; + struct bpf_mount_opts *opts = sb->s_fs_info; struct inode *inode; int ret; + /* Mounting an instance of BPF FS requires privileges */ + if (fc->user_ns != &init_user_ns && !capable(CAP_SYS_ADMIN)) + return -EPERM; + ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; @@ -811,7 +1040,7 @@ static int bpf_get_tree(struct fs_context *fc) static void bpf_free_fc(struct fs_context *fc) { - kfree(fc->fs_private); + kfree(fc->s_fs_info); } static const struct fs_context_operations bpf_context_ops = { @@ -835,17 +1064,32 @@ static int bpf_init_fs_context(struct fs_context *fc) opts->uid = current_fsuid(); opts->gid = current_fsgid(); - fc->fs_private = opts; + /* start out with no BPF token delegation enabled */ + opts->delegate_cmds = 0; + opts->delegate_maps = 0; + opts->delegate_progs = 0; + opts->delegate_attachs = 0; + + fc->s_fs_info = opts; fc->ops = &bpf_context_ops; return 0; } +static void bpf_kill_super(struct super_block *sb) +{ + struct bpf_mount_opts *opts = sb->s_fs_info; + + kill_litter_super(sb); + kfree(opts); +} + static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = bpf_fs_parameters, - .kill_sb = kill_litter_super, + .kill_sb = bpf_kill_super, + .fs_flags = FS_USERNS_MOUNT, }; static int __init bpf_init(void) diff --git a/kernel/bpf/log.c b/kernel/bpf/log.c index 594a234f122b..2a243cf37c60 100644 --- a/kernel/bpf/log.c +++ b/kernel/bpf/log.c @@ -9,6 +9,7 @@ #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/math64.h> +#include <linux/string.h> #define verbose(env, fmt, args...) bpf_verifier_log_write(env, fmt, ##args) @@ -333,7 +334,8 @@ find_linfo(const struct bpf_verifier_env *env, u32 insn_off) { const struct bpf_line_info *linfo; const struct bpf_prog *prog; - u32 i, nr_linfo; + u32 nr_linfo; + int l, r, m; prog = env->prog; nr_linfo = prog->aux->nr_linfo; @@ -342,11 +344,30 @@ find_linfo(const struct bpf_verifier_env *env, u32 insn_off) return NULL; linfo = prog->aux->linfo; - for (i = 1; i < nr_linfo; i++) - if (insn_off < linfo[i].insn_off) - break; + /* Loop invariant: linfo[l].insn_off <= insns_off. + * linfo[0].insn_off == 0 which always satisfies above condition. + * Binary search is searching for rightmost linfo entry that satisfies + * the above invariant, giving us the desired record that covers given + * instruction offset. + */ + l = 0; + r = nr_linfo - 1; + while (l < r) { + /* (r - l + 1) / 2 means we break a tie to the right, so if: + * l=1, r=2, linfo[l].insn_off <= insn_off, linfo[r].insn_off > insn_off, + * then m=2, we see that linfo[m].insn_off > insn_off, and so + * r becomes 1 and we exit the loop with correct l==1. + * If the tie was broken to the left, m=1 would end us up in + * an endless loop where l and m stay at 1 and r stays at 2. + */ + m = l + (r - l + 1) / 2; + if (linfo[m].insn_off <= insn_off) + l = m; + else + r = m - 1; + } - return &linfo[i - 1]; + return &linfo[l]; } static const char *ltrim(const char *s) @@ -361,13 +382,28 @@ __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, u32 insn_off, const char *prefix_fmt, ...) { - const struct bpf_line_info *linfo; + const struct bpf_line_info *linfo, *prev_linfo; + const struct btf *btf; + const char *s, *fname; if (!bpf_verifier_log_needed(&env->log)) return; + prev_linfo = env->prev_linfo; linfo = find_linfo(env, insn_off); - if (!linfo || linfo == env->prev_linfo) + if (!linfo || linfo == prev_linfo) + return; + + /* It often happens that two separate linfo records point to the same + * source code line, but have differing column numbers. Given verifier + * log doesn't emit column information, from user perspective we just + * end up emitting the same source code line twice unnecessarily. + * So instead check that previous and current linfo record point to + * the same file (file_name_offs match) and the same line number, and + * avoid emitting duplicated source code line in such case. + */ + if (prev_linfo && linfo->file_name_off == prev_linfo->file_name_off && + BPF_LINE_INFO_LINE_NUM(linfo->line_col) == BPF_LINE_INFO_LINE_NUM(prev_linfo->line_col)) return; if (prefix_fmt) { @@ -378,9 +414,15 @@ __printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env, va_end(args); } - verbose(env, "%s\n", - ltrim(btf_name_by_offset(env->prog->aux->btf, - linfo->line_off))); + btf = env->prog->aux->btf; + s = ltrim(btf_name_by_offset(btf, linfo->line_off)); + verbose(env, "%s", s); /* source code line */ + + s = btf_name_by_offset(btf, linfo->file_name_off); + /* leave only file name */ + fname = strrchr(s, '/'); + fname = fname ? fname + 1 : s; + verbose(env, " @ %s:%u\n", fname, BPF_LINE_INFO_LINE_NUM(linfo->line_col)); env->prev_linfo = linfo; } @@ -416,6 +458,7 @@ const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type) [PTR_TO_XDP_SOCK] = "xdp_sock", [PTR_TO_BTF_ID] = "ptr_", [PTR_TO_MEM] = "mem", + [PTR_TO_ARENA] = "arena", [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_MAP_KEY] = "map_key", @@ -651,6 +694,8 @@ static void print_reg_state(struct bpf_verifier_env *env, } verbose(env, "%s", reg_type_str(env, t)); + if (t == PTR_TO_ARENA) + return; if (t == PTR_TO_STACK) { if (state->frameno != reg->frameno) verbose(env, "[%d]", reg->frameno); diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index b32be680da6c..050fe1ebf0f7 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -164,13 +164,13 @@ static inline int extract_bit(const u8 *data, size_t index) */ static size_t longest_prefix_match(const struct lpm_trie *trie, const struct lpm_trie_node *node, - const struct bpf_lpm_trie_key *key) + const struct bpf_lpm_trie_key_u8 *key) { u32 limit = min(node->prefixlen, key->prefixlen); u32 prefixlen = 0, i = 0; BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32)); - BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32)); + BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key_u8, data) % sizeof(u32)); #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT) @@ -229,7 +229,7 @@ static void *trie_lookup_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *found = NULL; - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; if (key->prefixlen > trie->max_prefixlen) return NULL; @@ -309,7 +309,7 @@ static long trie_update_elem(struct bpf_map *map, struct lpm_trie *trie = container_of(map, struct lpm_trie, map); struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL; struct lpm_trie_node __rcu **slot; - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; unsigned long irq_flags; unsigned int next_bit; size_t matchlen = 0; @@ -437,7 +437,7 @@ out: static long trie_delete_elem(struct bpf_map *map, void *_key) { struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct bpf_lpm_trie_key *key = _key; + struct bpf_lpm_trie_key_u8 *key = _key; struct lpm_trie_node __rcu **trim, **trim2; struct lpm_trie_node *node, *parent; unsigned long irq_flags; @@ -536,7 +536,7 @@ out: sizeof(struct lpm_trie_node)) #define LPM_VAL_SIZE_MIN 1 -#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key) + (X)) +#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key_u8) + (X)) #define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX) #define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN) @@ -565,7 +565,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) /* copy mandatory map attributes */ bpf_map_init_from_attr(&trie->map, attr); trie->data_size = attr->key_size - - offsetof(struct bpf_lpm_trie_key, data); + offsetof(struct bpf_lpm_trie_key_u8, data); trie->max_prefixlen = trie->data_size * 8; spin_lock_init(&trie->lock); @@ -616,7 +616,7 @@ static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key) { struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root; struct lpm_trie *trie = container_of(map, struct lpm_trie, map); - struct bpf_lpm_trie_key *key = _key, *next_key = _next_key; + struct bpf_lpm_trie_key_u8 *key = _key, *next_key = _next_key; struct lpm_trie_node **node_stack = NULL; int err = 0, stack_ptr = -1; unsigned int next_bit; @@ -703,7 +703,7 @@ find_leftmost: } do_copy: next_key->prefixlen = next_node->prefixlen; - memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data), + memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key_u8, data), next_node->data, trie->data_size); free_stack: kfree(node_stack); @@ -715,7 +715,7 @@ static int trie_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) { - /* Keys must have struct bpf_lpm_trie_key embedded. */ + /* Keys must have struct bpf_lpm_trie_key_u8 embedded. */ return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ? -EINVAL : 0; } diff --git a/kernel/bpf/map_iter.c b/kernel/bpf/map_iter.c index 6abd7c5df4b3..9575314f40a6 100644 --- a/kernel/bpf/map_iter.c +++ b/kernel/bpf/map_iter.c @@ -213,9 +213,9 @@ __bpf_kfunc s64 bpf_map_sum_elem_count(const struct bpf_map *map) __bpf_kfunc_end_defs(); -BTF_SET8_START(bpf_map_iter_kfunc_ids) +BTF_KFUNCS_START(bpf_map_iter_kfunc_ids) BTF_ID_FLAGS(func, bpf_map_sum_elem_count, KF_TRUSTED_ARGS) -BTF_SET8_END(bpf_map_iter_kfunc_ids) +BTF_KFUNCS_END(bpf_map_iter_kfunc_ids) static const struct btf_kfunc_id_set bpf_map_iter_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index dff7ba539701..c99f8e5234ac 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -91,11 +91,14 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) } else if (value_size / 8 > sysctl_perf_event_max_stack) return ERR_PTR(-EINVAL); - /* hash table size must be power of 2 */ - n_buckets = roundup_pow_of_two(attr->max_entries); - if (!n_buckets) + /* hash table size must be power of 2; roundup_pow_of_two() can overflow + * into UB on 32-bit arches, so check that first + */ + if (attr->max_entries > 1UL << 31) return ERR_PTR(-E2BIG); + n_buckets = roundup_pow_of_two(attr->max_entries); + cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); if (!smap) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a1f18681721c..ae2ff73bde7e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -164,6 +164,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file, if (bpf_map_is_offloaded(map)) { return bpf_map_offload_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_CPUMAP || + map->map_type == BPF_MAP_TYPE_ARENA || map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { return map->ops->map_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_SOCKHASH || @@ -479,6 +480,39 @@ static void bpf_map_release_memcg(struct bpf_map *map) } #endif +int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid, + unsigned long nr_pages, struct page **pages) +{ + unsigned long i, j; + struct page *pg; + int ret = 0; +#ifdef CONFIG_MEMCG_KMEM + struct mem_cgroup *memcg, *old_memcg; + + memcg = bpf_map_get_memcg(map); + old_memcg = set_active_memcg(memcg); +#endif + for (i = 0; i < nr_pages; i++) { + pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0); + + if (pg) { + pages[i] = pg; + continue; + } + for (j = 0; j < i; j++) + __free_page(pages[j]); + ret = -ENOMEM; + break; + } + +#ifdef CONFIG_MEMCG_KMEM + set_active_memcg(old_memcg); + mem_cgroup_put(memcg); +#endif + return ret; +} + + static int btf_field_cmp(const void *a, const void *b) { const struct btf_field *f1 = a, *f2 = b; @@ -937,6 +971,21 @@ static __poll_t bpf_map_poll(struct file *filp, struct poll_table_struct *pts) return EPOLLERR; } +static unsigned long bpf_get_unmapped_area(struct file *filp, unsigned long addr, + unsigned long len, unsigned long pgoff, + unsigned long flags) +{ + struct bpf_map *map = filp->private_data; + + if (map->ops->map_get_unmapped_area) + return map->ops->map_get_unmapped_area(filp, addr, len, pgoff, flags); +#ifdef CONFIG_MMU + return current->mm->get_unmapped_area(filp, addr, len, pgoff, flags); +#else + return addr; +#endif +} + const struct file_operations bpf_map_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = bpf_map_show_fdinfo, @@ -946,6 +995,7 @@ const struct file_operations bpf_map_fops = { .write = bpf_dummy_write, .mmap = bpf_map_mmap, .poll = bpf_map_poll, + .get_unmapped_area = bpf_get_unmapped_area, }; int bpf_map_new_fd(struct bpf_map *map, int flags) @@ -1011,8 +1061,8 @@ int map_check_no_btf(const struct bpf_map *map, return -ENOTSUPP; } -static int map_check_btf(struct bpf_map *map, const struct btf *btf, - u32 btf_key_id, u32 btf_value_id) +static int map_check_btf(struct bpf_map *map, struct bpf_token *token, + const struct btf *btf, u32 btf_key_id, u32 btf_value_id) { const struct btf_type *key_type, *value_type; u32 key_size, value_size; @@ -1040,7 +1090,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!IS_ERR_OR_NULL(map->record)) { int i; - if (!bpf_capable()) { + if (!bpf_token_capable(token, CAP_BPF)) { ret = -EPERM; goto free_map_tab; } @@ -1123,14 +1173,21 @@ free_map_tab: return ret; } -#define BPF_MAP_CREATE_LAST_FIELD map_extra +static bool bpf_net_capable(void) +{ + return capable(CAP_NET_ADMIN) || capable(CAP_SYS_ADMIN); +} + +#define BPF_MAP_CREATE_LAST_FIELD map_token_fd /* called via syscall */ static int map_create(union bpf_attr *attr) { const struct bpf_map_ops *ops; + struct bpf_token *token = NULL; int numa_node = bpf_map_attr_numa_node(attr); u32 map_type = attr->map_type; struct bpf_map *map; + bool token_flag; int f_flags; int err; @@ -1138,6 +1195,12 @@ static int map_create(union bpf_attr *attr) if (err) return -EINVAL; + /* check BPF_F_TOKEN_FD flag, remember if it's set, and then clear it + * to avoid per-map type checks tripping on unknown flag + */ + token_flag = attr->map_flags & BPF_F_TOKEN_FD; + attr->map_flags &= ~BPF_F_TOKEN_FD; + if (attr->btf_vmlinux_value_type_id) { if (attr->map_type != BPF_MAP_TYPE_STRUCT_OPS || attr->btf_key_type_id || attr->btf_value_type_id) @@ -1147,6 +1210,7 @@ static int map_create(union bpf_attr *attr) } if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_type != BPF_MAP_TYPE_ARENA && attr->map_extra != 0) return -EINVAL; @@ -1178,14 +1242,32 @@ static int map_create(union bpf_attr *attr) if (!ops->map_mem_usage) return -EINVAL; + if (token_flag) { + token = bpf_token_get_from_fd(attr->map_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + + /* if current token doesn't grant map creation permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_MAP_CREATE) || + !bpf_token_allow_map_type(token, attr->map_type)) { + bpf_token_put(token); + token = NULL; + } + } + + err = -EPERM; + /* Intent here is for unprivileged_bpf_disabled to block BPF map * creation for unprivileged users; other actions depend * on fd availability and access to bpffs, so are dependent on * object creation success. Even with unprivileged BPF disabled, * capability checks are still carried out. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_token_capable(token, CAP_BPF)) + goto put_token; /* check privileged map type permissions */ switch (map_type) { @@ -1218,25 +1300,28 @@ static int map_create(union bpf_attr *attr) case BPF_MAP_TYPE_LRU_PERCPU_HASH: case BPF_MAP_TYPE_STRUCT_OPS: case BPF_MAP_TYPE_CPUMAP: - if (!bpf_capable()) - return -EPERM; + case BPF_MAP_TYPE_ARENA: + if (!bpf_token_capable(token, CAP_BPF)) + goto put_token; break; case BPF_MAP_TYPE_SOCKMAP: case BPF_MAP_TYPE_SOCKHASH: case BPF_MAP_TYPE_DEVMAP: case BPF_MAP_TYPE_DEVMAP_HASH: case BPF_MAP_TYPE_XSKMAP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; + if (!bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; break; default: WARN(1, "unsupported map type %d", map_type); - return -EPERM; + goto put_token; } map = ops->map_alloc(attr); - if (IS_ERR(map)) - return PTR_ERR(map); + if (IS_ERR(map)) { + err = PTR_ERR(map); + goto put_token; + } map->ops = ops; map->map_type = map_type; @@ -1273,7 +1358,7 @@ static int map_create(union bpf_attr *attr) map->btf = btf; if (attr->btf_value_type_id) { - err = map_check_btf(map, btf, attr->btf_key_type_id, + err = map_check_btf(map, token, btf, attr->btf_key_type_id, attr->btf_value_type_id); if (err) goto free_map; @@ -1285,15 +1370,16 @@ static int map_create(union bpf_attr *attr) attr->btf_vmlinux_value_type_id; } - err = security_bpf_map_alloc(map); + err = security_bpf_map_create(map, attr, token); if (err) - goto free_map; + goto free_map_sec; err = bpf_map_alloc_id(map); if (err) goto free_map_sec; bpf_map_save_memcg(map); + bpf_token_put(token); err = bpf_map_new_fd(map, f_flags); if (err < 0) { @@ -1314,6 +1400,8 @@ free_map_sec: free_map: btf_put(map->btf); map->ops->map_free(map); +put_token: + bpf_token_put(token); return err; } @@ -2144,7 +2232,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); free_uid(aux->user); - security_bpf_prog_free(aux); + security_bpf_prog_free(aux->prog); bpf_prog_free(aux->prog); } @@ -2160,7 +2248,7 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) btf_put(prog->aux->attach_btf); if (deferred) { - if (prog->aux->sleepable) + if (prog->sleepable) call_rcu_tasks_trace(&prog->aux->rcu, __bpf_prog_put_rcu); else call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); @@ -2590,13 +2678,15 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) } /* last field in 'union bpf_attr' used by this command */ -#define BPF_PROG_LOAD_LAST_FIELD log_true_size +#define BPF_PROG_LOAD_LAST_FIELD prog_token_fd static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) { enum bpf_prog_type type = attr->prog_type; struct bpf_prog *prog, *dst_prog = NULL; struct btf *attach_btf = NULL; + struct bpf_token *token = NULL; + bool bpf_cap; int err; char license[128]; @@ -2610,13 +2700,35 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) BPF_F_TEST_RND_HI32 | BPF_F_XDP_HAS_FRAGS | BPF_F_XDP_DEV_BOUND_ONLY | - BPF_F_TEST_REG_INVARIANTS)) + BPF_F_TEST_REG_INVARIANTS | + BPF_F_TOKEN_FD)) return -EINVAL; + bpf_prog_load_fixup_attach_type(attr); + + if (attr->prog_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->prog_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + /* if current token doesn't grant prog loading permissions, + * then we can't use this token, so ignore it and rely on + * system-wide capabilities checks + */ + if (!bpf_token_allow_cmd(token, BPF_PROG_LOAD) || + !bpf_token_allow_prog_type(token, attr->prog_type, + attr->expected_attach_type)) { + bpf_token_put(token); + token = NULL; + } + } + + bpf_cap = bpf_token_capable(token, CAP_BPF); + err = -EPERM; + if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && (attr->prog_flags & BPF_F_ANY_ALIGNMENT) && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; /* Intent here is for unprivileged_bpf_disabled to block BPF program * creation for unprivileged users; other actions depend @@ -2625,21 +2737,23 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) * capability checks are still carried out for these * and other operations. */ - if (sysctl_unprivileged_bpf_disabled && !bpf_capable()) - return -EPERM; + if (sysctl_unprivileged_bpf_disabled && !bpf_cap) + goto put_token; if (attr->insn_cnt == 0 || - attr->insn_cnt > (bpf_capable() ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) - return -E2BIG; + attr->insn_cnt > (bpf_cap ? BPF_COMPLEXITY_LIMIT_INSNS : BPF_MAXINSNS)) { + err = -E2BIG; + goto put_token; + } if (type != BPF_PROG_TYPE_SOCKET_FILTER && type != BPF_PROG_TYPE_CGROUP_SKB && - !bpf_capable()) - return -EPERM; + !bpf_cap) + goto put_token; - if (is_net_admin_prog_type(type) && !capable(CAP_NET_ADMIN) && !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (is_perfmon_prog_type(type) && !perfmon_capable()) - return -EPERM; + if (is_net_admin_prog_type(type) && !bpf_token_capable(token, CAP_NET_ADMIN)) + goto put_token; + if (is_perfmon_prog_type(type) && !bpf_token_capable(token, CAP_PERFMON)) + goto put_token; /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog * or btf, we need to check which one it is @@ -2649,27 +2763,33 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (IS_ERR(dst_prog)) { dst_prog = NULL; attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); - if (IS_ERR(attach_btf)) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = -EINVAL; + goto put_token; + } if (!btf_is_kernel(attach_btf)) { /* attaching through specifying bpf_prog's BTF * objects directly might be supported eventually */ btf_put(attach_btf); - return -ENOTSUPP; + err = -ENOTSUPP; + goto put_token; } } } else if (attr->attach_btf_id) { /* fall back to vmlinux BTF, if BTF type ID is specified */ attach_btf = bpf_get_btf_vmlinux(); - if (IS_ERR(attach_btf)) - return PTR_ERR(attach_btf); - if (!attach_btf) - return -EINVAL; + if (IS_ERR(attach_btf)) { + err = PTR_ERR(attach_btf); + goto put_token; + } + if (!attach_btf) { + err = -EINVAL; + goto put_token; + } btf_get(attach_btf); } - bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, attach_btf, attr->attach_btf_id, dst_prog)) { @@ -2677,7 +2797,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -EINVAL; + err = -EINVAL; + goto put_token; } /* plain bpf_prog allocation */ @@ -2687,20 +2808,21 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) bpf_prog_put(dst_prog); if (attach_btf) btf_put(attach_btf); - return -ENOMEM; + err = -EINVAL; + goto put_token; } prog->expected_attach_type = attr->expected_attach_type; + prog->sleepable = !!(attr->prog_flags & BPF_F_SLEEPABLE); prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; prog->aux->dev_bound = !!attr->prog_ifindex; - prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; - err = security_bpf_prog_alloc(prog->aux); - if (err) - goto free_prog; + /* move token into prog->aux, reuse taken refcnt */ + prog->aux->token = token; + token = NULL; prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; @@ -2709,12 +2831,12 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (copy_from_bpfptr(prog->insns, make_bpfptr(attr->insns, uattr.is_kernel), bpf_prog_insn_size(prog)) != 0) - goto free_prog_sec; + goto free_prog; /* copy eBPF program license from user space */ if (strncpy_from_bpfptr(license, make_bpfptr(attr->license, uattr.is_kernel), sizeof(license) - 1) < 0) - goto free_prog_sec; + goto free_prog; license[sizeof(license) - 1] = 0; /* eBPF programs must be GPL compatible to use GPL-ed functions */ @@ -2728,14 +2850,14 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_dev_bound_init(prog, attr); if (err) - goto free_prog_sec; + goto free_prog; } if (type == BPF_PROG_TYPE_EXT && dst_prog && bpf_prog_is_dev_bound(dst_prog->aux)) { err = bpf_prog_dev_bound_inherit(prog, dst_prog); if (err) - goto free_prog_sec; + goto free_prog; } /* @@ -2757,12 +2879,16 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr, u32 uattr_size) /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog_sec; + goto free_prog; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) + goto free_prog; + + err = security_bpf_prog_load(prog, attr, token); + if (err) goto free_prog_sec; /* run eBPF verifier */ @@ -2808,13 +2934,16 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->real_func_cnt); return err; + free_prog_sec: - free_uid(prog->aux->user); - security_bpf_prog_free(prog->aux); + security_bpf_prog_free(prog); free_prog: + free_uid(prog->aux->user); if (prog->aux->attach_btf) btf_put(prog->aux->attach_btf); bpf_prog_free(prog); +put_token: + bpf_token_put(token); return err; } @@ -3501,6 +3630,7 @@ static int bpf_perf_link_fill_kprobe(const struct perf_event *event, if (!kallsyms_show_value(current_cred())) addr = 0; info->perf_event.kprobe.addr = addr; + info->perf_event.kprobe.cookie = event->bpf_cookie; return 0; } #endif @@ -3526,6 +3656,7 @@ static int bpf_perf_link_fill_uprobe(const struct perf_event *event, else info->perf_event.type = BPF_PERF_EVENT_UPROBE; info->perf_event.uprobe.offset = offset; + info->perf_event.uprobe.cookie = event->bpf_cookie; return 0; } #endif @@ -3553,6 +3684,7 @@ static int bpf_perf_link_fill_tracepoint(const struct perf_event *event, uname = u64_to_user_ptr(info->perf_event.tracepoint.tp_name); ulen = info->perf_event.tracepoint.name_len; info->perf_event.type = BPF_PERF_EVENT_TRACEPOINT; + info->perf_event.tracepoint.cookie = event->bpf_cookie; return bpf_perf_link_fill_common(event, uname, ulen, NULL, NULL, NULL, NULL); } @@ -3561,6 +3693,7 @@ static int bpf_perf_link_fill_perf_event(const struct perf_event *event, { info->perf_event.event.type = event->attr.type; info->perf_event.event.config = event->attr.config; + info->perf_event.event.cookie = event->bpf_cookie; info->perf_event.type = BPF_PERF_EVENT_EVENT; return 0; } @@ -3818,7 +3951,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, case BPF_PROG_TYPE_SK_LOOKUP: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: - if (!capable(CAP_NET_ADMIN)) + if (!bpf_token_capable(prog->aux->token, CAP_NET_ADMIN)) /* cg-skb progs can be loaded by unpriv user. * check permissions at attach time. */ @@ -4021,7 +4154,7 @@ static int bpf_prog_detach(const union bpf_attr *attr) static int bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { - if (!capable(CAP_NET_ADMIN)) + if (!bpf_net_capable()) return -EPERM; if (CHECK_ATTR(BPF_PROG_QUERY)) return -EINVAL; @@ -4320,6 +4453,12 @@ static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog, continue; } + if ((BPF_CLASS(code) == BPF_LDX || BPF_CLASS(code) == BPF_STX || + BPF_CLASS(code) == BPF_ST) && BPF_MODE(code) == BPF_PROBE_MEM32) { + insns[i].code = BPF_CLASS(code) | BPF_SIZE(code) | BPF_MEM; + continue; + } + if (code != (BPF_LD | BPF_IMM | BPF_DW)) continue; @@ -4687,6 +4826,8 @@ static int bpf_map_get_info_by_fd(struct file *file, info.btf_value_type_id = map->btf_value_type_id; } info.btf_vmlinux_value_type_id = map->btf_vmlinux_value_type_id; + if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) + bpf_map_struct_ops_info_fill(&info, map); if (bpf_map_is_offloaded(map)) { err = bpf_map_offload_info_fill(&info, map); @@ -4789,15 +4930,34 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } -#define BPF_BTF_LOAD_LAST_FIELD btf_log_true_size +#define BPF_BTF_LOAD_LAST_FIELD btf_token_fd static int bpf_btf_load(const union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size) { + struct bpf_token *token = NULL; + if (CHECK_ATTR(BPF_BTF_LOAD)) return -EINVAL; - if (!bpf_capable()) + if (attr->btf_flags & ~BPF_F_TOKEN_FD) + return -EINVAL; + + if (attr->btf_flags & BPF_F_TOKEN_FD) { + token = bpf_token_get_from_fd(attr->btf_token_fd); + if (IS_ERR(token)) + return PTR_ERR(token); + if (!bpf_token_allow_cmd(token, BPF_BTF_LOAD)) { + bpf_token_put(token); + token = NULL; + } + } + + if (!bpf_token_capable(token, CAP_BPF)) { + bpf_token_put(token); return -EPERM; + } + + bpf_token_put(token); return btf_new_fd(attr, uattr, uattr_size); } @@ -5394,7 +5554,7 @@ static int bpf_prog_bind_map(union bpf_attr *attr) /* The bpf program will not access the bpf map, but for the sake of * simplicity, increase sleepable_refcnt for sleepable program as well. */ - if (prog->aux->sleepable) + if (prog->sleepable) atomic64_inc(&map->sleepable_refcnt); memcpy(used_maps_new, used_maps_old, sizeof(used_maps_old[0]) * prog->aux->used_map_cnt); @@ -5415,6 +5575,20 @@ out_prog_put: return ret; } +#define BPF_TOKEN_CREATE_LAST_FIELD token_create.bpffs_fd + +static int token_create(union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_TOKEN_CREATE)) + return -EINVAL; + + /* no flags are supported yet */ + if (attr->token_create.flags) + return -EINVAL; + + return bpf_token_create(attr); +} + static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) { union bpf_attr attr; @@ -5548,6 +5722,9 @@ static int __sys_bpf(int cmd, bpfptr_t uattr, unsigned int size) case BPF_PROG_BIND_MAP: err = bpf_prog_bind_map(&attr); break; + case BPF_TOKEN_CREATE: + err = token_create(&attr); + break; default: err = -EINVAL; break; @@ -5654,7 +5831,7 @@ static const struct bpf_func_proto bpf_sys_bpf_proto = { const struct bpf_func_proto * __weak tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } BPF_CALL_1(bpf_sys_close, u32, fd) @@ -5704,7 +5881,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_sys_bpf: - return !perfmon_capable() ? NULL : &bpf_sys_bpf_proto; + return !bpf_token_capable(prog->aux->token, CAP_PERFMON) + ? NULL : &bpf_sys_bpf_proto; case BPF_FUNC_btf_find_by_name_kind: return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index e5c3500443c6..ec4e97c61eef 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -978,6 +978,8 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) != __alignof__(struct bpf_iter_task)); + kit->pos = NULL; + switch (flags) { case BPF_TASK_ITER_ALL_THREADS: case BPF_TASK_ITER_ALL_PROCS: diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c new file mode 100644 index 000000000000..d6ccf8d00eab --- /dev/null +++ b/kernel/bpf/token.c @@ -0,0 +1,278 @@ +#include <linux/bpf.h> +#include <linux/vmalloc.h> +#include <linux/fdtable.h> +#include <linux/file.h> +#include <linux/fs.h> +#include <linux/kernel.h> +#include <linux/idr.h> +#include <linux/namei.h> +#include <linux/user_namespace.h> +#include <linux/security.h> + +static bool bpf_ns_capable(struct user_namespace *ns, int cap) +{ + return ns_capable(ns, cap) || (cap != CAP_SYS_ADMIN && ns_capable(ns, CAP_SYS_ADMIN)); +} + +bool bpf_token_capable(const struct bpf_token *token, int cap) +{ + struct user_namespace *userns; + + /* BPF token allows ns_capable() level of capabilities */ + userns = token ? token->userns : &init_user_ns; + if (!bpf_ns_capable(userns, cap)) + return false; + if (token && security_bpf_token_capable(token, cap) < 0) + return false; + return true; +} + +void bpf_token_inc(struct bpf_token *token) +{ + atomic64_inc(&token->refcnt); +} + +static void bpf_token_free(struct bpf_token *token) +{ + security_bpf_token_free(token); + put_user_ns(token->userns); + kfree(token); +} + +static void bpf_token_put_deferred(struct work_struct *work) +{ + struct bpf_token *token = container_of(work, struct bpf_token, work); + + bpf_token_free(token); +} + +void bpf_token_put(struct bpf_token *token) +{ + if (!token) + return; + + if (!atomic64_dec_and_test(&token->refcnt)) + return; + + INIT_WORK(&token->work, bpf_token_put_deferred); + schedule_work(&token->work); +} + +static int bpf_token_release(struct inode *inode, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + + bpf_token_put(token); + return 0; +} + +static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp) +{ + struct bpf_token *token = filp->private_data; + u64 mask; + + BUILD_BUG_ON(__MAX_BPF_CMD >= 64); + mask = BIT_ULL(__MAX_BPF_CMD) - 1; + if ((token->allowed_cmds & mask) == mask) + seq_printf(m, "allowed_cmds:\tany\n"); + else + seq_printf(m, "allowed_cmds:\t0x%llx\n", token->allowed_cmds); + + BUILD_BUG_ON(__MAX_BPF_MAP_TYPE >= 64); + mask = BIT_ULL(__MAX_BPF_MAP_TYPE) - 1; + if ((token->allowed_maps & mask) == mask) + seq_printf(m, "allowed_maps:\tany\n"); + else + seq_printf(m, "allowed_maps:\t0x%llx\n", token->allowed_maps); + + BUILD_BUG_ON(__MAX_BPF_PROG_TYPE >= 64); + mask = BIT_ULL(__MAX_BPF_PROG_TYPE) - 1; + if ((token->allowed_progs & mask) == mask) + seq_printf(m, "allowed_progs:\tany\n"); + else + seq_printf(m, "allowed_progs:\t0x%llx\n", token->allowed_progs); + + BUILD_BUG_ON(__MAX_BPF_ATTACH_TYPE >= 64); + mask = BIT_ULL(__MAX_BPF_ATTACH_TYPE) - 1; + if ((token->allowed_attachs & mask) == mask) + seq_printf(m, "allowed_attachs:\tany\n"); + else + seq_printf(m, "allowed_attachs:\t0x%llx\n", token->allowed_attachs); +} + +#define BPF_TOKEN_INODE_NAME "bpf-token" + +static const struct inode_operations bpf_token_iops = { }; + +static const struct file_operations bpf_token_fops = { + .release = bpf_token_release, + .show_fdinfo = bpf_token_show_fdinfo, +}; + +int bpf_token_create(union bpf_attr *attr) +{ + struct bpf_mount_opts *mnt_opts; + struct bpf_token *token = NULL; + struct user_namespace *userns; + struct inode *inode; + struct file *file; + struct path path; + struct fd f; + umode_t mode; + int err, fd; + + f = fdget(attr->token_create.bpffs_fd); + if (!f.file) + return -EBADF; + + path = f.file->f_path; + path_get(&path); + fdput(f); + + if (path.dentry != path.mnt->mnt_sb->s_root) { + err = -EINVAL; + goto out_path; + } + if (path.mnt->mnt_sb->s_op != &bpf_super_ops) { + err = -EINVAL; + goto out_path; + } + err = path_permission(&path, MAY_ACCESS); + if (err) + goto out_path; + + userns = path.dentry->d_sb->s_user_ns; + /* + * Enforce that creators of BPF tokens are in the same user + * namespace as the BPF FS instance. This makes reasoning about + * permissions a lot easier and we can always relax this later. + */ + if (current_user_ns() != userns) { + err = -EPERM; + goto out_path; + } + if (!ns_capable(userns, CAP_BPF)) { + err = -EPERM; + goto out_path; + } + + /* Creating BPF token in init_user_ns doesn't make much sense. */ + if (current_user_ns() == &init_user_ns) { + err = -EOPNOTSUPP; + goto out_path; + } + + mnt_opts = path.dentry->d_sb->s_fs_info; + if (mnt_opts->delegate_cmds == 0 && + mnt_opts->delegate_maps == 0 && + mnt_opts->delegate_progs == 0 && + mnt_opts->delegate_attachs == 0) { + err = -ENOENT; /* no BPF token delegation is set up */ + goto out_path; + } + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + inode = bpf_get_inode(path.mnt->mnt_sb, NULL, mode); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + goto out_path; + } + + inode->i_op = &bpf_token_iops; + inode->i_fop = &bpf_token_fops; + clear_nlink(inode); /* make sure it is unlinked */ + + file = alloc_file_pseudo(inode, path.mnt, BPF_TOKEN_INODE_NAME, O_RDWR, &bpf_token_fops); + if (IS_ERR(file)) { + iput(inode); + err = PTR_ERR(file); + goto out_path; + } + + token = kzalloc(sizeof(*token), GFP_USER); + if (!token) { + err = -ENOMEM; + goto out_file; + } + + atomic64_set(&token->refcnt, 1); + + /* remember bpffs owning userns for future ns_capable() checks */ + token->userns = get_user_ns(userns); + + token->allowed_cmds = mnt_opts->delegate_cmds; + token->allowed_maps = mnt_opts->delegate_maps; + token->allowed_progs = mnt_opts->delegate_progs; + token->allowed_attachs = mnt_opts->delegate_attachs; + + err = security_bpf_token_create(token, attr, &path); + if (err) + goto out_token; + + fd = get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + err = fd; + goto out_token; + } + + file->private_data = token; + fd_install(fd, file); + + path_put(&path); + return fd; + +out_token: + bpf_token_free(token); +out_file: + fput(file); +out_path: + path_put(&path); + return err; +} + +struct bpf_token *bpf_token_get_from_fd(u32 ufd) +{ + struct fd f = fdget(ufd); + struct bpf_token *token; + + if (!f.file) + return ERR_PTR(-EBADF); + if (f.file->f_op != &bpf_token_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + token = f.file->private_data; + bpf_token_inc(token); + fdput(f); + + return token; +} + +bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd) +{ + if (!token) + return false; + if (!(token->allowed_cmds & BIT_ULL(cmd))) + return false; + return security_bpf_token_cmd(token, cmd) == 0; +} + +bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type) +{ + if (!token || type >= __MAX_BPF_MAP_TYPE) + return false; + + return token->allowed_maps & BIT_ULL(type); +} + +bool bpf_token_allow_prog_type(const struct bpf_token *token, + enum bpf_prog_type prog_type, + enum bpf_attach_type attach_type) +{ + if (!token || prog_type >= __MAX_BPF_PROG_TYPE || attach_type >= __MAX_BPF_ATTACH_TYPE) + return false; + + return (token->allowed_progs & BIT_ULL(prog_type)) && + (token->allowed_attachs & BIT_ULL(attach_type)); +} diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index d382f5ebe06c..db7599c59c78 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -1014,7 +1014,7 @@ void notrace __bpf_tramp_exit(struct bpf_tramp_image *tr) bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) { - bool sleepable = prog->aux->sleepable; + bool sleepable = prog->sleepable; if (bpf_prog_check_recur(prog)) return sleepable ? __bpf_prog_enter_sleepable_recur : @@ -1029,7 +1029,7 @@ bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog) bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog) { - bool sleepable = prog->aux->sleepable; + bool sleepable = prog->sleepable; if (bpf_prog_check_recur(prog)) return sleepable ? __bpf_prog_exit_sleepable_recur : diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 65f598694d55..63749ad5ac6b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -528,6 +528,21 @@ static bool is_sync_callback_calling_insn(struct bpf_insn *insn) (bpf_pseudo_kfunc_call(insn) && is_sync_callback_calling_kfunc(insn->imm)); } +static bool is_async_callback_calling_insn(struct bpf_insn *insn) +{ + return bpf_helper_call(insn) && is_async_callback_calling_function(insn->imm); +} + +static bool is_may_goto_insn(struct bpf_insn *insn) +{ + return insn->code == (BPF_JMP | BPF_JCOND) && insn->src_reg == BPF_MAY_GOTO; +} + +static bool is_may_goto_insn_at(struct bpf_verifier_env *env, int insn_idx) +{ + return is_may_goto_insn(&env->prog->insnsi[insn_idx]); +} + static bool is_storage_get_function(enum bpf_func_id func_id) { return func_id == BPF_FUNC_sk_storage_get || @@ -1155,6 +1170,12 @@ static bool is_spilled_scalar_reg(const struct bpf_stack_state *stack) stack->spilled_ptr.type == SCALAR_VALUE; } +static bool is_spilled_scalar_reg64(const struct bpf_stack_state *stack) +{ + return stack->slot_type[0] == STACK_SPILL && + stack->spilled_ptr.type == SCALAR_VALUE; +} + /* Mark stack slot as STACK_MISC, unless it is already STACK_INVALID, in which * case they are equivalent, or it's STACK_ZERO, in which case we preserve * more precise STACK_ZERO. @@ -1418,6 +1439,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->dfs_depth = src->dfs_depth; dst_state->callback_unroll_depth = src->callback_unroll_depth; dst_state->used_as_loop_entry = src->used_as_loop_entry; + dst_state->may_goto_depth = src->may_goto_depth; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -2264,8 +2286,7 @@ static void __reg_assign_32_into_64(struct bpf_reg_state *reg) } /* Mark a register as having a completely unknown (scalar) value. */ -static void __mark_reg_unknown(const struct bpf_verifier_env *env, - struct bpf_reg_state *reg) +static void __mark_reg_unknown_imprecise(struct bpf_reg_state *reg) { /* * Clear type, off, and union(map_ptr, range) and @@ -2277,10 +2298,20 @@ static void __mark_reg_unknown(const struct bpf_verifier_env *env, reg->ref_obj_id = 0; reg->var_off = tnum_unknown; reg->frameno = 0; - reg->precise = !env->bpf_capable; + reg->precise = false; __mark_reg_unbounded(reg); } +/* Mark a register as having a completely unknown (scalar) value, + * initialize .precise as true when not bpf capable. + */ +static void __mark_reg_unknown(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg) +{ + __mark_reg_unknown_imprecise(reg); + reg->precise = !env->bpf_capable; +} + static void mark_reg_unknown(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno) { @@ -4355,6 +4386,7 @@ static bool is_spillable_regtype(enum bpf_reg_type type) case PTR_TO_MEM: case PTR_TO_FUNC: case PTR_TO_MAP_KEY: + case PTR_TO_ARENA: return true; default: return false; @@ -4380,20 +4412,6 @@ static u64 reg_const_value(struct bpf_reg_state *reg, bool subreg32) return subreg32 ? tnum_subreg(reg->var_off).value : reg->var_off.value; } -static bool __is_scalar_unbounded(struct bpf_reg_state *reg) -{ - return tnum_is_unknown(reg->var_off) && - reg->smin_value == S64_MIN && reg->smax_value == S64_MAX && - reg->umin_value == 0 && reg->umax_value == U64_MAX && - reg->s32_min_value == S32_MIN && reg->s32_max_value == S32_MAX && - reg->u32_min_value == 0 && reg->u32_max_value == U32_MAX; -} - -static bool register_is_bounded(struct bpf_reg_state *reg) -{ - return reg->type == SCALAR_VALUE && !__is_scalar_unbounded(reg); -} - static bool __is_pointer_value(bool allow_ptr_leaks, const struct bpf_reg_state *reg) { @@ -4403,6 +4421,18 @@ static bool __is_pointer_value(bool allow_ptr_leaks, return reg->type != SCALAR_VALUE; } +static void assign_scalar_id_before_mov(struct bpf_verifier_env *env, + struct bpf_reg_state *src_reg) +{ + if (src_reg->type == SCALAR_VALUE && !src_reg->id && + !tnum_is_const(src_reg->var_off)) + /* Ensure that src_reg has a valid ID that will be copied to + * dst_reg and then will be used by find_equal_scalars() to + * propagate min/max range. + */ + src_reg->id = ++env->id_gen; +} + /* Copy src state preserving dst->parent and dst->live fields */ static void copy_register_state(struct bpf_reg_state *dst, const struct bpf_reg_state *src) { @@ -4438,6 +4468,11 @@ static bool is_bpf_st_mem(struct bpf_insn *insn) return BPF_CLASS(insn->code) == BPF_ST && BPF_MODE(insn->code) == BPF_MEM; } +static int get_reg_width(struct bpf_reg_state *reg) +{ + return fls64(reg->umax_value); +} + /* check_stack_{read,write}_fixed_off functions track spill/fill of registers, * stack boundary and alignment are checked in check_mem_access() */ @@ -4487,13 +4522,19 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env, return err; mark_stack_slot_scratched(env, spi); - if (reg && !(off % BPF_REG_SIZE) && register_is_bounded(reg) && env->bpf_capable) { + if (reg && !(off % BPF_REG_SIZE) && reg->type == SCALAR_VALUE && env->bpf_capable) { + bool reg_value_fits; + + reg_value_fits = get_reg_width(reg) <= BITS_PER_BYTE * size; + /* Make sure that reg had an ID to build a relation on spill. */ + if (reg_value_fits) + assign_scalar_id_before_mov(env, reg); save_register_state(env, state, spi, reg, size); /* Break the relation on a narrowing spill. */ - if (fls64(reg->umax_value) > BITS_PER_BYTE * size) + if (!reg_value_fits) state->stack[spi].spilled_ptr.id = 0; } else if (!reg && !(off % BPF_REG_SIZE) && is_bpf_st_mem(insn) && - insn->imm != 0 && env->bpf_capable) { + env->bpf_capable) { struct bpf_reg_state fake_reg = {}; __mark_reg_known(&fake_reg, insn->imm); @@ -4640,7 +4681,20 @@ static int check_stack_write_var_off(struct bpf_verifier_env *env, return -EINVAL; } - /* Erase all spilled pointers. */ + /* If writing_zero and the spi slot contains a spill of value 0, + * maintain the spill type. + */ + if (writing_zero && *stype == STACK_SPILL && + is_spilled_scalar_reg(&state->stack[spi])) { + struct bpf_reg_state *spill_reg = &state->stack[spi].spilled_ptr; + + if (tnum_is_const(spill_reg->var_off) && spill_reg->var_off.value == 0) { + zero_used = true; + continue; + } + } + + /* Erase all other spilled pointers. */ state->stack[spi].spilled_ptr.type = NOT_INIT; /* Update the slot type. */ @@ -4756,7 +4810,8 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, if (dst_regno < 0) return 0; - if (!(off % BPF_REG_SIZE) && size == spill_size) { + if (size <= spill_size && + bpf_stack_narrow_access_ok(off, size, spill_size)) { /* The earlier check_reg_arg() has decided the * subreg_def for this insn. Save it first. */ @@ -4764,6 +4819,12 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env, copy_register_state(&state->regs[dst_regno], reg); state->regs[dst_regno].subreg_def = subreg_def; + + /* Break the relation on a narrowing fill. + * coerce_reg_to_size will adjust the boundaries. + */ + if (get_reg_width(reg) > size * BITS_PER_BYTE) + state->regs[dst_regno].id = 0; } else { int spill_cnt = 0, zero_cnt = 0; @@ -5211,6 +5272,11 @@ bad_type: return -EINVAL; } +static bool in_sleepable(struct bpf_verifier_env *env) +{ + return env->prog->sleepable; +} + /* The non-sleepable programs and sleepable programs with explicit bpf_rcu_read_lock() * can dereference RCU protected pointers and result is PTR_TRUSTED. */ @@ -5218,7 +5284,7 @@ static bool in_rcu_cs(struct bpf_verifier_env *env) { return env->cur_state->active_rcu_lock || env->cur_state->active_lock.ptr || - !env->prog->aux->sleepable; + !in_sleepable(env); } /* Once GCC supports btf_type_tag the following mechanism will be replaced with tag check */ @@ -5227,7 +5293,9 @@ BTF_ID(struct, prog_test_ref_kfunc) #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) #endif +#ifdef CONFIG_BPF_JIT BTF_ID(struct, bpf_cpumask) +#endif BTF_ID(struct, task_struct) BTF_SET_END(rcu_protected_types) @@ -5761,6 +5829,8 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, case PTR_TO_XDP_SOCK: pointer_desc = "xdp_sock "; break; + case PTR_TO_ARENA: + return 0; default: break; } @@ -5768,6 +5838,17 @@ static int check_ptr_alignment(struct bpf_verifier_env *env, strict); } +static int round_up_stack_depth(struct bpf_verifier_env *env, int stack_depth) +{ + if (env->prog->jit_requested) + return round_up(stack_depth, 16); + + /* round up to 32-bytes, since this is granularity + * of interpreter stack size + */ + return round_up(max_t(u32, stack_depth, 1), 32); +} + /* starting from main bpf function walk all instructions of the function * and recursively walk all callees that given function can call. * Ignore jump and exit insns. @@ -5811,10 +5892,7 @@ process_func: depth); return -EACCES; } - /* round up to 32-bytes, since this is granularity - * of interpreter stack size - */ - depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); + depth += round_up_stack_depth(env, subprog[idx].stack_depth); if (depth > MAX_BPF_STACK) { verbose(env, "combined stack size of %d calls is %d. Too large\n", frame + 1, depth); @@ -5908,7 +5986,7 @@ continue_func: */ if (frame == 0) return 0; - depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); + depth -= round_up_stack_depth(env, subprog[idx].stack_depth); frame--; i = ret_insn[frame]; idx = ret_prog[frame]; @@ -6039,10 +6117,10 @@ static void coerce_reg_to_size(struct bpf_reg_state *reg, int size) * values are also truncated so we push 64-bit bounds into * 32-bit bounds. Above were truncated < 32-bits already. */ - if (size < 4) { + if (size < 4) __mark_reg32_unbounded(reg); - reg_bounds_sync(reg); - } + + reg_bounds_sync(reg); } static void set_sext64_default_val(struct bpf_reg_state *reg, int size) @@ -6862,6 +6940,9 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (!err && value_regno >= 0 && (rdonly_mem || t == BPF_READ)) mark_reg_unknown(env, regs, value_regno); + } else if (reg->type == PTR_TO_ARENA) { + if (t == BPF_READ && value_regno >= 0) + mark_reg_unknown(env, regs, value_regno); } else { verbose(env, "R%d invalid mem access '%s'\n", regno, reg_type_str(env, reg->type)); @@ -8198,6 +8279,7 @@ found: switch ((int)reg->type) { case PTR_TO_BTF_ID: case PTR_TO_BTF_ID | PTR_TRUSTED: + case PTR_TO_BTF_ID | PTR_TRUSTED | PTR_MAYBE_NULL: case PTR_TO_BTF_ID | MEM_RCU: case PTR_TO_BTF_ID | PTR_MAYBE_NULL: case PTR_TO_BTF_ID | PTR_MAYBE_NULL | MEM_RCU: @@ -8332,6 +8414,7 @@ static int check_func_arg_reg_off(struct bpf_verifier_env *env, case PTR_TO_MEM | MEM_RINGBUF: case PTR_TO_BUF: case PTR_TO_BUF | MEM_RDONLY: + case PTR_TO_ARENA: case SCALAR_VALUE: return 0; /* All the rest must be rejected, except PTR_TO_BTF_ID which allows @@ -9296,10 +9379,34 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog, bpf_log(log, "arg#%d is expected to be non-NULL\n", i); return -EINVAL; } + } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { + /* + * Can pass any value and the kernel won't crash, but + * only PTR_TO_ARENA or SCALAR make sense. Everything + * else is a bug in the bpf program. Point it out to + * the user at the verification time instead of + * run-time debug nightmare. + */ + if (reg->type != PTR_TO_ARENA && reg->type != SCALAR_VALUE) { + bpf_log(log, "R%d is not a pointer to arena or scalar.\n", regno); + return -EINVAL; + } } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) { ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0); if (ret) return ret; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { + struct bpf_call_arg_meta meta; + int err; + + if (register_is_null(reg) && type_may_be_null(arg->arg_type)) + continue; + + memset(&meta, 0, sizeof(meta)); /* leave func_id as zero */ + err = check_reg_type(env, regno, arg->arg_type, &arg->btf_id, &meta); + err = err ?: check_func_arg_reg_off(env, reg, regno, arg->arg_type); + if (err) + return err; } else { bpf_log(log, "verifier bug: unrecognized arg#%d type %d\n", i, arg->arg_type); @@ -9375,9 +9482,7 @@ static int push_callback_call(struct bpf_verifier_env *env, struct bpf_insn *ins return -EFAULT; } - if (insn->code == (BPF_JMP | BPF_CALL) && - insn->src_reg == 0 && - insn->imm == BPF_FUNC_timer_set_callback) { + if (is_async_callback_calling_insn(insn)) { struct bpf_verifier_state *async_cb; /* there is no real recursion here. timer callbacks are async */ @@ -9436,6 +9541,13 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (subprog_is_global(env, subprog)) { const char *sub_name = subprog_name(env, subprog); + /* Only global subprogs cannot be called with a lock held. */ + if (env->cur_state->active_lock.ptr) { + verbose(env, "global function calls are not allowed while holding a lock,\n" + "use static function instead\n"); + return -EINVAL; + } + if (err) { verbose(env, "Caller passes invalid args into func#%d ('%s')\n", subprog, sub_name); @@ -10092,7 +10204,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (!env->prog->aux->sleepable && fn->might_sleep) { + if (!in_sleepable(env) && fn->might_sleep) { verbose(env, "helper call might sleep in a non-sleepable prog\n"); return -EINVAL; } @@ -10122,7 +10234,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EINVAL; } - if (env->prog->aux->sleepable && is_storage_get_function(func_id)) + if (in_sleepable(env) && is_storage_get_function(func_id)) env->insn_aux_data[insn_idx].storage_get_func_atomic = true; } @@ -10618,24 +10730,6 @@ static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_RCU_PROTECTED; } -static bool __kfunc_param_match_suffix(const struct btf *btf, - const struct btf_param *arg, - const char *suffix) -{ - int suffix_len = strlen(suffix), len; - const char *param_name; - - /* In the future, this can be ported to use BTF tagging */ - param_name = btf_name_by_offset(btf, arg->name_off); - if (str_is_empty(param_name)) - return false; - len = strlen(param_name); - if (len < suffix_len) - return false; - param_name += len - suffix_len; - return !strncmp(param_name, suffix, suffix_len); -} - static bool is_kfunc_arg_mem_size(const struct btf *btf, const struct btf_param *arg, const struct bpf_reg_state *reg) @@ -10646,7 +10740,7 @@ static bool is_kfunc_arg_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__sz"); + return btf_param_match_suffix(btf, arg, "__sz"); } static bool is_kfunc_arg_const_mem_size(const struct btf *btf, @@ -10659,47 +10753,52 @@ static bool is_kfunc_arg_const_mem_size(const struct btf *btf, if (!btf_type_is_scalar(t) || reg->type != SCALAR_VALUE) return false; - return __kfunc_param_match_suffix(btf, arg, "__szk"); + return btf_param_match_suffix(btf, arg, "__szk"); } static bool is_kfunc_arg_optional(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__opt"); + return btf_param_match_suffix(btf, arg, "__opt"); } static bool is_kfunc_arg_constant(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__k"); + return btf_param_match_suffix(btf, arg, "__k"); } static bool is_kfunc_arg_ignore(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__ign"); + return btf_param_match_suffix(btf, arg, "__ign"); +} + +static bool is_kfunc_arg_map(const struct btf *btf, const struct btf_param *arg) +{ + return btf_param_match_suffix(btf, arg, "__map"); } static bool is_kfunc_arg_alloc_obj(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__alloc"); + return btf_param_match_suffix(btf, arg, "__alloc"); } static bool is_kfunc_arg_uninit(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__uninit"); + return btf_param_match_suffix(btf, arg, "__uninit"); } static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr"); + return btf_param_match_suffix(btf, arg, "__refcounted_kptr"); } static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__nullable"); + return btf_param_match_suffix(btf, arg, "__nullable"); } static bool is_kfunc_arg_const_str(const struct btf *btf, const struct btf_param *arg) { - return __kfunc_param_match_suffix(btf, arg, "__str"); + return btf_param_match_suffix(btf, arg, "__str"); } static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, @@ -10846,6 +10945,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_RB_NODE, KF_ARG_PTR_TO_NULL, KF_ARG_PTR_TO_CONST_STR, + KF_ARG_PTR_TO_MAP, }; enum special_kfunc_type { @@ -10969,7 +11069,7 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, * type to our caller. When a set of conditions hold in the BTF type of * arguments, we resolve it to a known kfunc_ptr_arg_type. */ - if (btf_get_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) + if (btf_is_prog_ctx_type(&env->log, meta->btf, t, resolve_prog_type(env->prog), argno)) return KF_ARG_PTR_TO_CTX; if (is_kfunc_arg_alloc_obj(meta->btf, &args[argno])) @@ -10999,6 +11099,9 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_const_str(meta->btf, &args[argno])) return KF_ARG_PTR_TO_CONST_STR; + if (is_kfunc_arg_map(meta->btf, &args[argno])) + return KF_ARG_PTR_TO_MAP; + if ((base_type(reg->type) == PTR_TO_BTF_ID || reg2btf_ids[base_type(reg->type)])) { if (!btf_type_is_struct(ref_t)) { verbose(env, "kernel function %s args#%d pointer type %s %s is not supported\n", @@ -11481,7 +11584,7 @@ static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env) return true; fallthrough; default: - return env->prog->aux->sleepable; + return in_sleepable(env); } } @@ -11599,6 +11702,7 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ switch (kf_arg_type) { case KF_ARG_PTR_TO_NULL: continue; + case KF_ARG_PTR_TO_MAP: case KF_ARG_PTR_TO_ALLOC_BTF_ID: case KF_ARG_PTR_TO_BTF_ID: if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) @@ -11815,6 +11919,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ if (ret < 0) return ret; break; + case KF_ARG_PTR_TO_MAP: + /* If argument has '__map' suffix expect 'struct bpf_map *' */ + ref_id = *reg2btf_ids[CONST_PTR_TO_MAP]; + ref_t = btf_type_by_id(btf_vmlinux, ref_id); + ref_tname = btf_name_by_offset(btf, ref_t->name_off); + fallthrough; case KF_ARG_PTR_TO_BTF_ID: /* Only base_type is checked, further checks are done here */ if ((base_type(reg->type) != PTR_TO_BTF_ID || @@ -12002,7 +12112,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, } sleepable = is_kfunc_sleepable(&meta); - if (sleepable && !env->prog->aux->sleepable) { + if (sleepable && !in_sleepable(env)) { verbose(env, "program must be sleepable to call sleepable kfunc %s\n", func_name); return -EACCES; } @@ -12289,6 +12399,9 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, meta.func_name); return -EFAULT; } + } else if (btf_type_is_void(ptr_type)) { + /* kfunc returning 'void *' is equivalent to returning scalar */ + mark_reg_unknown(env, regs, BPF_REG_0); } else if (!__btf_type_is_struct(ptr_type)) { if (!meta.r0_size) { __u32 sz; @@ -12826,6 +12939,19 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, } switch (base_type(ptr_reg->type)) { + case PTR_TO_CTX: + case PTR_TO_MAP_VALUE: + case PTR_TO_MAP_KEY: + case PTR_TO_STACK: + case PTR_TO_PACKET_META: + case PTR_TO_PACKET: + case PTR_TO_TP_BUFFER: + case PTR_TO_BTF_ID: + case PTR_TO_MEM: + case PTR_TO_BUF: + case PTR_TO_FUNC: + case CONST_PTR_TO_DYNPTR: + break; case PTR_TO_FLOW_KEYS: if (known) break; @@ -12835,16 +12961,10 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (known && smin_val == 0 && opcode == BPF_ADD) break; fallthrough; - case PTR_TO_PACKET_END: - case PTR_TO_SOCKET: - case PTR_TO_SOCK_COMMON: - case PTR_TO_TCP_SOCK: - case PTR_TO_XDP_SOCK: + default: verbose(env, "R%d pointer arithmetic on %s prohibited\n", dst, reg_type_str(env, ptr_reg->type)); return -EACCES; - default: - break; } /* In case of 'scalar += pointer', dst_reg inherits pointer type and id. @@ -13751,6 +13871,21 @@ static int adjust_reg_min_max_vals(struct bpf_verifier_env *env, dst_reg = ®s[insn->dst_reg]; src_reg = NULL; + + if (dst_reg->type == PTR_TO_ARENA) { + struct bpf_insn_aux_data *aux = cur_aux(env); + + if (BPF_CLASS(insn->code) == BPF_ALU64) + /* + * 32-bit operations zero upper bits automatically. + * 64-bit operations need to be converted to 32. + */ + aux->needs_zext = true; + + /* Any arithmetic operations are allowed on arena pointers */ + return 0; + } + if (dst_reg->type != SCALAR_VALUE) ptr_reg = dst_reg; else @@ -13868,19 +14003,20 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) } else if (opcode == BPF_MOV) { if (BPF_SRC(insn->code) == BPF_X) { - if (insn->imm != 0) { - verbose(env, "BPF_MOV uses reserved fields\n"); - return -EINVAL; - } - if (BPF_CLASS(insn->code) == BPF_ALU) { - if (insn->off != 0 && insn->off != 8 && insn->off != 16) { + if ((insn->off != 0 && insn->off != 8 && insn->off != 16) || + insn->imm) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } + } else if (insn->off == BPF_ADDR_SPACE_CAST) { + if (insn->imm != 1 && insn->imm != 1u << 16) { + verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n"); + return -EINVAL; + } } else { - if (insn->off != 0 && insn->off != 8 && insn->off != 16 && - insn->off != 32) { + if ((insn->off != 0 && insn->off != 8 && insn->off != 16 && + insn->off != 32) || insn->imm) { verbose(env, "BPF_MOV uses reserved fields\n"); return -EINVAL; } @@ -13905,20 +14041,18 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) if (BPF_SRC(insn->code) == BPF_X) { struct bpf_reg_state *src_reg = regs + insn->src_reg; struct bpf_reg_state *dst_reg = regs + insn->dst_reg; - bool need_id = src_reg->type == SCALAR_VALUE && !src_reg->id && - !tnum_is_const(src_reg->var_off); if (BPF_CLASS(insn->code) == BPF_ALU64) { - if (insn->off == 0) { + if (insn->imm) { + /* off == BPF_ADDR_SPACE_CAST */ + mark_reg_unknown(env, regs, insn->dst_reg); + if (insn->imm == 1) /* cast from as(1) to as(0) */ + dst_reg->type = PTR_TO_ARENA; + } else if (insn->off == 0) { /* case: R1 = R2 * copy register state to dest reg */ - if (need_id) - /* Assign src and dst registers the same ID - * that will be used by find_equal_scalars() - * to propagate min/max range. - */ - src_reg->id = ++env->id_gen; + assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); dst_reg->live |= REG_LIVE_WRITTEN; dst_reg->subreg_def = DEF_NOT_SUBREG; @@ -13933,8 +14067,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) bool no_sext; no_sext = src_reg->umax_value < (1ULL << (insn->off - 1)); - if (no_sext && need_id) - src_reg->id = ++env->id_gen; + if (no_sext) + assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); if (!no_sext) dst_reg->id = 0; @@ -13954,10 +14088,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EACCES; } else if (src_reg->type == SCALAR_VALUE) { if (insn->off == 0) { - bool is_src_reg_u32 = src_reg->umax_value <= U32_MAX; + bool is_src_reg_u32 = get_reg_width(src_reg) <= 32; - if (is_src_reg_u32 && need_id) - src_reg->id = ++env->id_gen; + if (is_src_reg_u32) + assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); /* Make sure ID is cleared if src_reg is not in u32 * range otherwise dst_reg min/max could be incorrectly @@ -13971,8 +14105,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn) /* case: W1 = (s8, s16)W2 */ bool no_sext = src_reg->umax_value < (1ULL << (insn->off - 1)); - if (no_sext && need_id) - src_reg->id = ++env->id_gen; + if (no_sext) + assign_scalar_id_before_mov(env, src_reg); copy_register_state(dst_reg, src_reg); if (!no_sext) dst_reg->id = 0; @@ -14807,11 +14941,36 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env, int err; /* Only conditional jumps are expected to reach here. */ - if (opcode == BPF_JA || opcode > BPF_JSLE) { + if (opcode == BPF_JA || opcode > BPF_JCOND) { verbose(env, "invalid BPF_JMP/JMP32 opcode %x\n", opcode); return -EINVAL; } + if (opcode == BPF_JCOND) { + struct bpf_verifier_state *cur_st = env->cur_state, *queued_st, *prev_st; + int idx = *insn_idx; + + if (insn->code != (BPF_JMP | BPF_JCOND) || + insn->src_reg != BPF_MAY_GOTO || + insn->dst_reg || insn->imm || insn->off == 0) { + verbose(env, "invalid may_goto off %d imm %d\n", + insn->off, insn->imm); + return -EINVAL; + } + prev_st = find_prev_entry(env, cur_st->parent, idx); + + /* branch out 'fallthrough' insn as a new state to explore */ + queued_st = push_stack(env, idx + 1, idx, false); + if (!queued_st) + return -ENOMEM; + + queued_st->may_goto_depth++; + if (prev_st) + widen_imprecise_scalars(env, prev_st, queued_st); + *insn_idx += insn->off; + return 0; + } + /* check src2 operand */ err = check_reg_arg(env, insn->dst_reg, SRC_OP); if (err) @@ -15063,6 +15222,10 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) if (insn->src_reg == BPF_PSEUDO_MAP_VALUE || insn->src_reg == BPF_PSEUDO_MAP_IDX_VALUE) { + if (map->map_type == BPF_MAP_TYPE_ARENA) { + __mark_reg_unknown(env, dst_reg); + return 0; + } dst_reg->type = PTR_TO_MAP_VALUE; dst_reg->off = aux->map_off; WARN_ON_ONCE(map->max_entries != 1); @@ -15529,7 +15692,7 @@ static int visit_insn(int t, struct bpf_verifier_env *env) return DONE_EXPLORING; case BPF_CALL: - if (insn->src_reg == 0 && insn->imm == BPF_FUNC_timer_set_callback) + if (is_async_callback_calling_insn(insn)) /* Mark this call insn as a prune point to trigger * is_state_visited() check before call itself is * processed by __check_func_call(). Otherwise new @@ -15595,6 +15758,8 @@ static int visit_insn(int t, struct bpf_verifier_env *env) default: /* conditional jump with two edges */ mark_prune_point(env, t); + if (is_may_goto_insn(insn)) + mark_force_checkpoint(env, t); ret = push_insn(t, t + 1, FALLTHROUGH, env); if (ret) @@ -16158,8 +16323,8 @@ static int check_btf_info(struct bpf_verifier_env *env, } /* check %cur's range satisfies %old's */ -static bool range_within(struct bpf_reg_state *old, - struct bpf_reg_state *cur) +static bool range_within(const struct bpf_reg_state *old, + const struct bpf_reg_state *cur) { return old->umin_value <= cur->umin_value && old->umax_value >= cur->umax_value && @@ -16323,21 +16488,28 @@ static bool regs_exact(const struct bpf_reg_state *rold, check_ids(rold->ref_obj_id, rcur->ref_obj_id, idmap); } +enum exact_level { + NOT_EXACT, + EXACT, + RANGE_WITHIN +}; + /* Returns true if (rold safe implies rcur safe) */ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, - struct bpf_reg_state *rcur, struct bpf_idmap *idmap, bool exact) + struct bpf_reg_state *rcur, struct bpf_idmap *idmap, + enum exact_level exact) { - if (exact) + if (exact == EXACT) return regs_exact(rold, rcur, idmap); - if (!(rold->live & REG_LIVE_READ)) + if (!(rold->live & REG_LIVE_READ) && exact == NOT_EXACT) /* explored state didn't use this */ return true; - if (rold->type == NOT_INIT) - /* explored state can't have used this */ - return true; - if (rcur->type == NOT_INIT) - return false; + if (rold->type == NOT_INIT) { + if (exact == NOT_EXACT || rcur->type == NOT_INIT) + /* explored state can't have used this */ + return true; + } /* Enforce that register types have to match exactly, including their * modifiers (like PTR_MAYBE_NULL, MEM_RDONLY, etc), as a general @@ -16372,7 +16544,7 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, return memcmp(rold, rcur, offsetof(struct bpf_reg_state, id)) == 0 && check_scalar_ids(rold->id, rcur->id, idmap); } - if (!rold->precise) + if (!rold->precise && exact == NOT_EXACT) return true; /* Why check_ids() for scalar registers? * @@ -16440,13 +16612,53 @@ static bool regsafe(struct bpf_verifier_env *env, struct bpf_reg_state *rold, * the same stack frame, since fp-8 in foo != fp-8 in bar */ return regs_exact(rold, rcur, idmap) && rold->frameno == rcur->frameno; + case PTR_TO_ARENA: + return true; default: return regs_exact(rold, rcur, idmap); } } +static struct bpf_reg_state unbound_reg; + +static __init int unbound_reg_init(void) +{ + __mark_reg_unknown_imprecise(&unbound_reg); + unbound_reg.live |= REG_LIVE_READ; + return 0; +} +late_initcall(unbound_reg_init); + +static bool is_stack_all_misc(struct bpf_verifier_env *env, + struct bpf_stack_state *stack) +{ + u32 i; + + for (i = 0; i < ARRAY_SIZE(stack->slot_type); ++i) { + if ((stack->slot_type[i] == STACK_MISC) || + (stack->slot_type[i] == STACK_INVALID && env->allow_uninit_stack)) + continue; + return false; + } + + return true; +} + +static struct bpf_reg_state *scalar_reg_for_stack(struct bpf_verifier_env *env, + struct bpf_stack_state *stack) +{ + if (is_spilled_scalar_reg64(stack)) + return &stack->spilled_ptr; + + if (is_stack_all_misc(env, stack)) + return &unbound_reg; + + return NULL; +} + static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, - struct bpf_func_state *cur, struct bpf_idmap *idmap, bool exact) + struct bpf_func_state *cur, struct bpf_idmap *idmap, + enum exact_level exact) { int i, spi; @@ -16459,12 +16671,13 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, spi = i / BPF_REG_SIZE; - if (exact && + if (exact != NOT_EXACT && old->stack[spi].slot_type[i % BPF_REG_SIZE] != cur->stack[spi].slot_type[i % BPF_REG_SIZE]) return false; - if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) && !exact) { + if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ) + && exact == NOT_EXACT) { i += BPF_REG_SIZE - 1; /* explored state didn't use this */ continue; @@ -16483,6 +16696,20 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old, if (i >= cur->allocated_stack) return false; + /* 64-bit scalar spill vs all slots MISC and vice versa. + * Load from all slots MISC produces unbound scalar. + * Construct a fake register for such stack and call + * regsafe() to ensure scalar ids are compared. + */ + old_reg = scalar_reg_for_stack(env, &old->stack[spi]); + cur_reg = scalar_reg_for_stack(env, &cur->stack[spi]); + if (old_reg && cur_reg) { + if (!regsafe(env, old_reg, cur_reg, idmap, exact)) + return false; + i += BPF_REG_SIZE - 1; + continue; + } + /* if old state was safe with misc data in the stack * it will be safe with zero-initialized stack. * The opposite is not true @@ -16596,10 +16823,13 @@ static bool refsafe(struct bpf_func_state *old, struct bpf_func_state *cur, * the current state will reach 'bpf_exit' instruction safely */ static bool func_states_equal(struct bpf_verifier_env *env, struct bpf_func_state *old, - struct bpf_func_state *cur, bool exact) + struct bpf_func_state *cur, enum exact_level exact) { int i; + if (old->callback_depth > cur->callback_depth) + return false; + for (i = 0; i < MAX_BPF_REG; i++) if (!regsafe(env, &old->regs[i], &cur->regs[i], &env->idmap_scratch, exact)) @@ -16623,7 +16853,7 @@ static void reset_idmap_scratch(struct bpf_verifier_env *env) static bool states_equal(struct bpf_verifier_env *env, struct bpf_verifier_state *old, struct bpf_verifier_state *cur, - bool exact) + enum exact_level exact) { int i; @@ -16997,7 +17227,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * => unsafe memory access at 11 would not be caught. */ if (is_iter_next_insn(env, insn_idx)) { - if (states_equal(env, &sl->state, cur, true)) { + if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) { struct bpf_func_state *cur_frame; struct bpf_reg_state *iter_state, *iter_reg; int spi; @@ -17020,15 +17250,23 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) } goto skip_inf_loop_check; } + if (is_may_goto_insn_at(env, insn_idx)) { + if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) { + update_loop_entry(cur, &sl->state); + goto hit; + } + goto skip_inf_loop_check; + } if (calls_callback(env, insn_idx)) { - if (states_equal(env, &sl->state, cur, true)) + if (states_equal(env, &sl->state, cur, RANGE_WITHIN)) goto hit; goto skip_inf_loop_check; } /* attempt to detect infinite loop to avoid unnecessary doomed work */ if (states_maybe_looping(&sl->state, cur) && - states_equal(env, &sl->state, cur, false) && + states_equal(env, &sl->state, cur, EXACT) && !iter_active_depths_differ(&sl->state, cur) && + sl->state.may_goto_depth == cur->may_goto_depth && sl->state.callback_unroll_depth == cur->callback_unroll_depth) { verbose_linfo(env, insn_idx, "; "); verbose(env, "infinite loop detected at insn %d\n", insn_idx); @@ -17084,7 +17322,7 @@ skip_inf_loop_check: */ loop_entry = get_loop_entry(&sl->state); force_exact = loop_entry && loop_entry->branches > 0; - if (states_equal(env, &sl->state, cur, force_exact)) { + if (states_equal(env, &sl->state, cur, force_exact ? RANGE_WITHIN : NOT_EXACT)) { if (force_exact) update_loop_entry(cur, loop_entry); hit: @@ -17254,6 +17492,7 @@ static bool reg_type_mismatch_ok(enum bpf_reg_type type) case PTR_TO_TCP_SOCK: case PTR_TO_XDP_SOCK: case PTR_TO_BTF_ID: + case PTR_TO_ARENA: return false; default: return true; @@ -17536,7 +17775,6 @@ static int do_check(struct bpf_verifier_env *env) if (env->cur_state->active_lock.ptr) { if ((insn->src_reg == BPF_REG_0 && insn->imm != BPF_FUNC_spin_unlock) || - (insn->src_reg == BPF_PSEUDO_CALL) || (insn->src_reg == BPF_PSEUDO_KFUNC_CALL && (insn->off != 0 || !is_bpf_graph_api_kfunc(insn->imm)))) { verbose(env, "function calls are not allowed while holding a lock\n"); @@ -17584,14 +17822,12 @@ static int do_check(struct bpf_verifier_env *env) return -EINVAL; } process_bpf_exit_full: - if (env->cur_state->active_lock.ptr && - !in_rbtree_lock_required_cb(env)) { + if (env->cur_state->active_lock.ptr && !env->cur_state->curframe) { verbose(env, "bpf_spin_unlock is missing\n"); return -EINVAL; } - if (env->cur_state->active_rcu_lock && - !in_rbtree_lock_required_cb(env)) { + if (env->cur_state->active_rcu_lock && !env->cur_state->curframe) { verbose(env, "bpf_rcu_read_unlock is missing\n"); return -EINVAL; } @@ -17904,7 +18140,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, return -EINVAL; } - if (prog->aux->sleepable) + if (prog->sleepable) switch (map->map_type) { case BPF_MAP_TYPE_HASH: case BPF_MAP_TYPE_LRU_HASH: @@ -17920,6 +18156,9 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, case BPF_MAP_TYPE_SK_STORAGE: case BPF_MAP_TYPE_TASK_STORAGE: case BPF_MAP_TYPE_CGRP_STORAGE: + case BPF_MAP_TYPE_QUEUE: + case BPF_MAP_TYPE_STACK: + case BPF_MAP_TYPE_ARENA: break; default: verbose(env, @@ -18089,7 +18328,7 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) return -E2BIG; } - if (env->prog->aux->sleepable) + if (env->prog->sleepable) atomic64_inc(&map->sleepable_refcnt); /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it @@ -18107,6 +18346,31 @@ static int resolve_pseudo_ldimm64(struct bpf_verifier_env *env) fdput(f); return -EBUSY; } + if (map->map_type == BPF_MAP_TYPE_ARENA) { + if (env->prog->aux->arena) { + verbose(env, "Only one arena per program\n"); + fdput(f); + return -EBUSY; + } + if (!env->allow_ptr_leaks || !env->bpf_capable) { + verbose(env, "CAP_BPF and CAP_PERFMON are required to use arena\n"); + fdput(f); + return -EPERM; + } + if (!env->prog->jit_requested) { + verbose(env, "JIT is required to use arena\n"); + return -EOPNOTSUPP; + } + if (!bpf_jit_supports_arena()) { + verbose(env, "JIT doesn't support arena\n"); + return -EOPNOTSUPP; + } + env->prog->aux->arena = (void *)map; + if (!bpf_arena_get_user_vm_start(env->prog->aux->arena)) { + verbose(env, "arena's user address must be set via map_extra or mmap()\n"); + return -EINVAL; + } + } fdput(f); next_insn: @@ -18728,6 +18992,14 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env) env->prog->aux->num_exentries++; } continue; + case PTR_TO_ARENA: + if (BPF_MODE(insn->code) == BPF_MEMSX) { + verbose(env, "sign extending loads from arena are not supported yet\n"); + return -EOPNOTSUPP; + } + insn->code = BPF_CLASS(insn->code) | BPF_PROBE_MEM32 | BPF_SIZE(insn->code); + env->prog->aux->num_exentries++; + continue; default: continue; } @@ -18913,13 +19185,19 @@ static int jit_subprogs(struct bpf_verifier_env *env) func[i]->aux->nr_linfo = prog->aux->nr_linfo; func[i]->aux->jited_linfo = prog->aux->jited_linfo; func[i]->aux->linfo_idx = env->subprog_info[i].linfo_idx; + func[i]->aux->arena = prog->aux->arena; num_exentries = 0; insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (BPF_CLASS(insn->code) == BPF_LDX && (BPF_MODE(insn->code) == BPF_PROBE_MEM || + BPF_MODE(insn->code) == BPF_PROBE_MEM32 || BPF_MODE(insn->code) == BPF_PROBE_MEMSX)) num_exentries++; + if ((BPF_CLASS(insn->code) == BPF_STX || + BPF_CLASS(insn->code) == BPF_ST) && + BPF_MODE(insn->code) == BPF_PROBE_MEM32) + num_exentries++; } func[i]->aux->num_exentries = num_exentries; func[i]->aux->tail_call_reachable = env->subprog_info[i].tail_call_reachable; @@ -19294,7 +19572,10 @@ static int do_misc_fixups(struct bpf_verifier_env *env) struct bpf_insn insn_buf[16]; struct bpf_prog *new_prog; struct bpf_map *map_ptr; - int i, ret, cnt, delta = 0; + int i, ret, cnt, delta = 0, cur_subprog = 0; + struct bpf_subprog_info *subprogs = env->subprog_info; + u16 stack_depth = subprogs[cur_subprog].stack_depth; + u16 stack_depth_extra = 0; if (env->seen_exception && !env->exception_callback_subprog) { struct bpf_insn patch[] = { @@ -19314,7 +19595,22 @@ static int do_misc_fixups(struct bpf_verifier_env *env) mark_subprog_exc_cb(env, env->exception_callback_subprog); } - for (i = 0; i < insn_cnt; i++, insn++) { + for (i = 0; i < insn_cnt;) { + if (insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->imm) { + if ((insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1) || + (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) { + /* convert to 32-bit mov that clears upper 32-bit */ + insn->code = BPF_ALU | BPF_MOV | BPF_X; + /* clear off, so it's a normal 'wX = wY' from JIT pov */ + insn->off = 0; + } /* cast from as(0) to as(1) should be handled by JIT */ + goto next_insn; + } + + if (env->insn_aux_data[i + delta].needs_zext) + /* Convert BPF_CLASS(insn->code) == BPF_ALU64 to 32-bit ALU */ + insn->code = BPF_ALU | BPF_OP(insn->code) | BPF_SRC(insn->code); + /* Make divide-by-zero exceptions impossible. */ if (insn->code == (BPF_ALU64 | BPF_MOD | BPF_X) || insn->code == (BPF_ALU64 | BPF_DIV | BPF_X) || @@ -19353,7 +19649,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement LD_ABS and LD_IND with a rewrite, if supported by the program type. */ @@ -19373,7 +19669,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Rewrite pointer arithmetic to mitigate speculation attacks. */ @@ -19388,7 +19684,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) aux = &env->insn_aux_data[i + delta]; if (!aux->alu_state || aux->alu_state == BPF_ALU_NON_POINTER) - continue; + goto next_insn; isneg = aux->alu_state & BPF_ALU_NEG_VALUE; issrc = (aux->alu_state & BPF_ALU_SANITIZE) == @@ -19426,19 +19722,39 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; + } + + if (is_may_goto_insn(insn)) { + int stack_off = -stack_depth - 8; + + stack_depth_extra = 8; + insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_AX, BPF_REG_10, stack_off); + insn_buf[1] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_AX, 0, insn->off + 2); + insn_buf[2] = BPF_ALU64_IMM(BPF_SUB, BPF_REG_AX, 1); + insn_buf[3] = BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_AX, stack_off); + cnt = 4; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; } if (insn->code != (BPF_JMP | BPF_CALL)) - continue; + goto next_insn; if (insn->src_reg == BPF_PSEUDO_CALL) - continue; + goto next_insn; if (insn->src_reg == BPF_PSEUDO_KFUNC_CALL) { ret = fixup_kfunc_call(env, insn, insn_buf, i + delta, &cnt); if (ret) return ret; if (cnt == 0) - continue; + goto next_insn; new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); if (!new_prog) @@ -19447,7 +19763,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } if (insn->imm == BPF_FUNC_get_route_realm) @@ -19495,11 +19811,11 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } insn->imm = ret + 1; - continue; + goto next_insn; } if (!bpf_map_ptr_unpriv(aux)) - continue; + goto next_insn; /* instead of changing every JIT dealing with tail_call * emit two extra insns: @@ -19528,7 +19844,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } if (insn->imm == BPF_FUNC_timer_set_callback) { @@ -19565,7 +19881,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) } if (is_storage_get_function(insn->imm)) { - if (!env->prog->aux->sleepable || + if (!in_sleepable(env) || env->insn_aux_data[i + delta].storage_get_func_atomic) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_ATOMIC); else @@ -19640,7 +19956,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } BUILD_BUG_ON(!__same_type(ops->map_lookup_elem, @@ -19671,31 +19987,31 @@ patch_map_ops_generic: switch (insn->imm) { case BPF_FUNC_map_lookup_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_elem); - continue; + goto next_insn; case BPF_FUNC_map_update_elem: insn->imm = BPF_CALL_IMM(ops->map_update_elem); - continue; + goto next_insn; case BPF_FUNC_map_delete_elem: insn->imm = BPF_CALL_IMM(ops->map_delete_elem); - continue; + goto next_insn; case BPF_FUNC_map_push_elem: insn->imm = BPF_CALL_IMM(ops->map_push_elem); - continue; + goto next_insn; case BPF_FUNC_map_pop_elem: insn->imm = BPF_CALL_IMM(ops->map_pop_elem); - continue; + goto next_insn; case BPF_FUNC_map_peek_elem: insn->imm = BPF_CALL_IMM(ops->map_peek_elem); - continue; + goto next_insn; case BPF_FUNC_redirect_map: insn->imm = BPF_CALL_IMM(ops->map_redirect); - continue; + goto next_insn; case BPF_FUNC_for_each_map_elem: insn->imm = BPF_CALL_IMM(ops->map_for_each_callback); - continue; + goto next_insn; case BPF_FUNC_map_lookup_percpu_elem: insn->imm = BPF_CALL_IMM(ops->map_lookup_percpu_elem); - continue; + goto next_insn; } goto patch_call_imm; @@ -19723,7 +20039,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_arg inline. */ @@ -19748,7 +20064,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_ret inline. */ @@ -19776,7 +20092,7 @@ patch_map_ops_generic: delta += cnt - 1; env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement get_func_arg_cnt inline. */ @@ -19791,7 +20107,7 @@ patch_map_ops_generic: env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } /* Implement bpf_get_func_ip inline. */ @@ -19806,9 +20122,26 @@ patch_map_ops_generic: env->prog = prog = new_prog; insn = new_prog->insnsi + i + delta; - continue; + goto next_insn; } + /* Implement bpf_kptr_xchg inline */ + if (prog->jit_requested && BITS_PER_LONG == 64 && + insn->imm == BPF_FUNC_kptr_xchg && + bpf_jit_supports_ptr_xchg()) { + insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_2); + insn_buf[1] = BPF_ATOMIC_OP(BPF_DW, BPF_XCHG, BPF_REG_1, BPF_REG_0, 0); + cnt = 2; + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + goto next_insn; + } patch_call_imm: fn = env->ops->get_func_proto(insn->imm, env->prog); /* all functions that have prototype and verifier allowed @@ -19821,6 +20154,40 @@ patch_call_imm: return -EFAULT; } insn->imm = fn->func - __bpf_call_base; +next_insn: + if (subprogs[cur_subprog + 1].start == i + delta + 1) { + subprogs[cur_subprog].stack_depth += stack_depth_extra; + subprogs[cur_subprog].stack_extra = stack_depth_extra; + cur_subprog++; + stack_depth = subprogs[cur_subprog].stack_depth; + stack_depth_extra = 0; + } + i++; + insn++; + } + + env->prog->aux->stack_depth = subprogs[0].stack_depth; + for (i = 0; i < env->subprog_cnt; i++) { + int subprog_start = subprogs[i].start; + int stack_slots = subprogs[i].stack_extra / 8; + + if (!stack_slots) + continue; + if (stack_slots > 1) { + verbose(env, "verifier bug: stack_slots supports may_goto only\n"); + return -EFAULT; + } + + /* Add ST insn to subprog prologue to init extra stack */ + insn_buf[0] = BPF_ST_MEM(BPF_DW, BPF_REG_FP, + -subprogs[i].stack_depth, BPF_MAX_LOOPS); + /* Copy first actual insn to preserve it */ + insn_buf[1] = env->prog->insnsi[subprog_start]; + + new_prog = bpf_patch_insn_data(env, subprog_start, insn_buf, 2); + if (!new_prog) + return -ENOMEM; + env->prog = prog = new_prog; } /* Since poke tab is now finalized, publish aux to tracker. */ @@ -20041,7 +20408,6 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) state->first_insn_idx = env->subprog_info[subprog].start; state->last_insn_idx = -1; - regs = state->frame[state->curframe]->regs; if (subprog || env->prog->type == BPF_PROG_TYPE_EXT) { const char *sub_name = subprog_name(env, subprog); @@ -20085,6 +20451,21 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog) mark_reg_known_zero(env, regs, i); reg->mem_size = arg->mem_size; reg->id = ++env->id_gen; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) { + reg->type = PTR_TO_BTF_ID; + if (arg->arg_type & PTR_MAYBE_NULL) + reg->type |= PTR_MAYBE_NULL; + if (arg->arg_type & PTR_UNTRUSTED) + reg->type |= PTR_UNTRUSTED; + if (arg->arg_type & PTR_TRUSTED) + reg->type |= PTR_TRUSTED; + mark_reg_known_zero(env, regs, i); + reg->btf = bpf_get_btf_vmlinux(); /* can't fail at this point */ + reg->btf_id = arg->btf_id; + reg->id = ++env->id_gen; + } else if (base_type(arg->arg_type) == ARG_PTR_TO_ARENA) { + /* caller can pass either PTR_TO_ARENA or SCALAR */ + mark_reg_unknown(env, regs, i); } else { WARN_ONCE(1, "BUG: unhandled arg#%d type %d\n", i - BPF_REG_1, arg->arg_type); @@ -20233,10 +20614,12 @@ static void print_verification_stats(struct bpf_verifier_env *env) static int check_struct_ops_btf_id(struct bpf_verifier_env *env) { const struct btf_type *t, *func_proto; + const struct bpf_struct_ops_desc *st_ops_desc; const struct bpf_struct_ops *st_ops; const struct btf_member *member; struct bpf_prog *prog = env->prog; u32 btf_id, member_idx; + struct btf *btf; const char *mname; if (!prog->gpl_compatible) { @@ -20244,15 +20627,30 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) return -EINVAL; } + if (!prog->aux->attach_btf_id) + return -ENOTSUPP; + + btf = prog->aux->attach_btf; + if (btf_is_module(btf)) { + /* Make sure st_ops is valid through the lifetime of env */ + env->attach_btf_mod = btf_try_get_module(btf); + if (!env->attach_btf_mod) { + verbose(env, "struct_ops module %s is not found\n", + btf_get_name(btf)); + return -ENOTSUPP; + } + } + btf_id = prog->aux->attach_btf_id; - st_ops = bpf_struct_ops_find(btf_id); - if (!st_ops) { + st_ops_desc = bpf_struct_ops_find(btf, btf_id); + if (!st_ops_desc) { verbose(env, "attach_btf_id %u is not a supported struct\n", btf_id); return -ENOTSUPP; } + st_ops = st_ops_desc->st_ops; - t = st_ops->type; + t = st_ops_desc->type; member_idx = prog->expected_attach_type; if (member_idx >= btf_type_vlen(t)) { verbose(env, "attach to invalid member idx %u of struct %s\n", @@ -20261,8 +20659,8 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } member = &btf_type_member(t)[member_idx]; - mname = btf_name_by_offset(btf_vmlinux, member->name_off); - func_proto = btf_type_resolve_func_ptr(btf_vmlinux, member->type, + mname = btf_name_by_offset(btf, member->name_off); + func_proto = btf_type_resolve_func_ptr(btf, member->type, NULL); if (!func_proto) { verbose(env, "attach to invalid member %s(@idx %u) of struct %s\n", @@ -20280,6 +20678,12 @@ static int check_struct_ops_btf_id(struct bpf_verifier_env *env) } } + /* btf_ctx_access() used this to provide argument type info */ + prog->aux->ctx_arg_info = + st_ops_desc->arg_info[member_idx].info; + prog->aux->ctx_arg_info_size = + st_ops_desc->arg_info[member_idx].cnt; + prog->aux->attach_func_proto = func_proto; prog->aux->attach_func_name = mname; env->ops = st_ops->verifier_ops; @@ -20537,7 +20941,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, } } - if (prog->aux->sleepable) { + if (prog->sleepable) { ret = -EINVAL; switch (prog->type) { case BPF_PROG_TYPE_TRACING: @@ -20648,14 +21052,14 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) u64 key; if (prog->type == BPF_PROG_TYPE_SYSCALL) { - if (prog->aux->sleepable) + if (prog->sleepable) /* attach_btf_id checked to be zero already */ return 0; verbose(env, "Syscall programs can only be sleepable\n"); return -EINVAL; } - if (prog->aux->sleepable && !can_be_sleepable(prog)) { + if (prog->sleepable && !can_be_sleepable(prog)) { verbose(env, "Only fentry/fexit/fmod_ret, lsm, iter, uprobe, and struct_ops programs can be sleepable\n"); return -EINVAL; } @@ -20764,7 +21168,12 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 env->prog = *prog; env->ops = bpf_verifier_ops[env->prog->type]; env->fd_array = make_bpfptr(attr->fd_array, uattr.is_kernel); - is_priv = bpf_capable(); + + env->allow_ptr_leaks = bpf_allow_ptr_leaks(env->prog->aux->token); + env->allow_uninit_stack = bpf_allow_uninit_stack(env->prog->aux->token); + env->bypass_spec_v1 = bpf_bypass_spec_v1(env->prog->aux->token); + env->bypass_spec_v4 = bpf_bypass_spec_v4(env->prog->aux->token); + env->bpf_capable = is_priv = bpf_token_capable(env->prog->aux->token, CAP_BPF); bpf_get_btf_vmlinux(); @@ -20796,12 +21205,6 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3 if (attr->prog_flags & BPF_F_ANY_ALIGNMENT) env->strict_alignment = false; - env->allow_ptr_leaks = bpf_allow_ptr_leaks(); - env->allow_uninit_stack = bpf_allow_uninit_stack(); - env->bypass_spec_v1 = bpf_bypass_spec_v1(); - env->bypass_spec_v4 = bpf_bypass_spec_v4(); - env->bpf_capable = bpf_capable(); - if (is_priv) env->test_state_freq = attr->prog_flags & BPF_F_TEST_STATE_FREQ; env->test_reg_invariants = attr->prog_flags & BPF_F_TEST_REG_INVARIANTS; @@ -20967,6 +21370,8 @@ err_release_maps: env->prog->expected_attach_type = 0; *prog = env->prog; + + module_put(env->attach_btf_mod); err_unlock: if (!is_priv) mutex_unlock(&bpf_verifier_lock); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index ba36c073304a..4237c8748715 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -2562,7 +2562,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, update_partition_sd_lb(cs, old_prs); out_free: free_cpumasks(NULL, &tmp); - return 0; + return retval; } /** @@ -2598,9 +2598,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (cpumask_equal(cs->exclusive_cpus, trialcs->exclusive_cpus)) return 0; - if (alloc_cpumasks(NULL, &tmp)) - return -ENOMEM; - if (*buf) compute_effective_exclusive_cpumask(trialcs, NULL); @@ -2615,6 +2612,9 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs, if (retval) return retval; + if (alloc_cpumasks(NULL, &tmp)) + return -ENOMEM; + if (old_prs) { if (cpumask_empty(trialcs->effective_xcpus)) { invalidate = true; @@ -3897,6 +3897,7 @@ static struct cftype legacy_files[] = { }, { + /* obsolete, may be removed in the future */ .name = "memory_spread_slab", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c index a8350d2d63e6..07e2284bb499 100644 --- a/kernel/cgroup/rstat.c +++ b/kernel/cgroup/rstat.c @@ -562,10 +562,10 @@ void cgroup_base_stat_cputime_show(struct seq_file *seq) } /* Add bpf kfuncs for cgroup_rstat_updated() and cgroup_rstat_flush() */ -BTF_SET8_START(bpf_rstat_kfunc_ids) +BTF_KFUNCS_START(bpf_rstat_kfunc_ids) BTF_ID_FLAGS(func, cgroup_rstat_updated) BTF_ID_FLAGS(func, cgroup_rstat_flush, KF_SLEEPABLE) -BTF_SET8_END(bpf_rstat_kfunc_ids) +BTF_KFUNCS_END(bpf_rstat_kfunc_ids) static const struct btf_kfunc_id_set bpf_rstat_kfunc_set = { .owner = THIS_MODULE, diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index 4722b998a324..509ee703de15 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -40,6 +40,12 @@ CONFIG_UBSAN_ENUM=y CONFIG_UBSAN_SHIFT=y CONFIG_UBSAN_UNREACHABLE=y # +# Networking Debugging +# +CONFIG_NET_DEV_REFCNT_TRACKER=y +CONFIG_NET_NS_REFCNT_TRACKER=y +CONFIG_DEBUG_NET=y +# # Memory Debugging # # CONFIG_DEBUG_PAGEALLOC is not set diff --git a/kernel/configs/hardening.config b/kernel/configs/hardening.config index 95a400f042b1..7a5bbfc024b7 100644 --- a/kernel/configs/hardening.config +++ b/kernel/configs/hardening.config @@ -44,7 +44,9 @@ CONFIG_UBSAN_BOUNDS=y # CONFIG_UBSAN_BOOL # CONFIG_UBSAN_ENUM # CONFIG_UBSAN_ALIGNMENT -CONFIG_UBSAN_SANITIZE_ALL=y + +# Sampling-based heap out-of-bounds and use-after-free detection. +CONFIG_KFENCE=y # Linked list integrity checking. CONFIG_LIST_HARDENED=y @@ -93,6 +95,3 @@ CONFIG_SYN_COOKIES=y # Attack surface reduction: Use the modern PTY interface (devpts) only. # CONFIG_LEGACY_PTYS is not set - -# Attack surface reduction: Use only modesetting video drivers. -# CONFIG_DRM_LEGACY is not set diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 6ef0b35fc28c..70ae70d03823 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -458,6 +458,8 @@ static __always_inline void context_tracking_recursion_exit(void) * __ct_user_enter - Inform the context tracking that the CPU is going * to enter user or guest space mode. * + * @state: userspace context-tracking state to enter. + * * This function must be called right before we switch from the kernel * to user or guest space, when it's guaranteed the remaining kernel * instructions to execute won't use any RCU read side critical section @@ -595,6 +597,8 @@ NOKPROBE_SYMBOL(user_enter_callable); * __ct_user_exit - Inform the context tracking that the CPU is * exiting user or guest mode and entering the kernel. * + * @state: userspace context-tracking state being exited from. + * * This function must be called after we entered the kernel from user or * guest space before any use of RCU read side critical section. This * potentially include any high level kernel code like syscalls, exceptions, diff --git a/kernel/cpu.c b/kernel/cpu.c index e6ec3ba4950b..8f6affd051f7 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -54,7 +54,6 @@ * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector - * @cpu: CPU number * @node: Remote CPU node; for multi-instance, do a * single entry callback for install/remove * @last: For multi-instance rollback, remember how far we got @@ -1324,10 +1323,6 @@ static int take_cpu_down(void *_param) */ cpuhp_invoke_callback_range_nofail(false, cpu, st, target); - /* Give up timekeeping duties */ - tick_handover_do_timer(); - /* Remove CPU from timer broadcasting */ - tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; @@ -1403,6 +1398,7 @@ void cpuhp_report_idle_dead(void) struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); + tick_assert_timekeeping_handover(); rcutree_report_cpu_dead(); st->state = CPUHP_AP_IDLE_DEAD; /* @@ -1909,14 +1905,14 @@ static bool __init cpuhp_bringup_cpus_parallel(unsigned int ncpus) static inline bool cpuhp_bringup_cpus_parallel(unsigned int ncpus) { return false; } #endif /* CONFIG_HOTPLUG_PARALLEL */ -void __init bringup_nonboot_cpus(unsigned int setup_max_cpus) +void __init bringup_nonboot_cpus(unsigned int max_cpus) { /* Try parallel bringup optimization if enabled */ - if (cpuhp_bringup_cpus_parallel(setup_max_cpus)) + if (cpuhp_bringup_cpus_parallel(max_cpus)) return; /* Full per CPU serialized bringup */ - cpuhp_bringup_mask(cpu_present_mask, setup_max_cpus, CPUHP_ONLINE); + cpuhp_bringup_mask(cpu_present_mask, max_cpus, CPUHP_ONLINE); } #ifdef CONFIG_PM_SLEEP_SMP @@ -2205,7 +2201,11 @@ static struct cpuhp_step cpuhp_hp_states[] = { .startup.single = NULL, .teardown.single = hrtimers_cpu_dying, }, - + [CPUHP_AP_TICK_DYING] = { + .name = "tick:dying", + .startup.single = NULL, + .teardown.single = tick_cpu_dying, + }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { @@ -3005,7 +3005,7 @@ static ssize_t control_show(struct device *dev, return sysfs_emit(buf, "%d\n", cpu_smt_num_threads); #endif - return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); + return sysfs_emit(buf, "%s\n", state); } static ssize_t control_store(struct device *dev, struct device_attribute *attr, @@ -3018,7 +3018,7 @@ static DEVICE_ATTR_RW(control); static ssize_t active_show(struct device *dev, struct device_attribute *attr, char *buf) { - return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); + return sysfs_emit(buf, "%d\n", sched_smt_active()); } static DEVICE_ATTR_RO(active); @@ -3107,10 +3107,10 @@ const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE -struct cpumask __cpu_possible_mask __read_mostly +struct cpumask __cpu_possible_mask __ro_after_init = {CPU_BITS_ALL}; #else -struct cpumask __cpu_possible_mask __read_mostly; +struct cpumask __cpu_possible_mask __ro_after_init; #endif EXPORT_SYMBOL(__cpu_possible_mask); diff --git a/kernel/crash_core.c b/kernel/crash_core.c index 75cd6a736d03..78b5dc7cee3a 100644 --- a/kernel/crash_core.c +++ b/kernel/crash_core.c @@ -11,9 +11,14 @@ #include <linux/sizes.h> #include <linux/kexec.h> #include <linux/memory.h> +#include <linux/mm.h> #include <linux/cpuhotplug.h> #include <linux/memblock.h> #include <linux/kmemleak.h> +#include <linux/crash_core.h> +#include <linux/reboot.h> +#include <linux/btf.h> +#include <linux/objtool.h> #include <asm/page.h> #include <asm/sections.h> @@ -26,451 +31,130 @@ /* Per cpu memory for storing cpu states in case of system crash. */ note_buf_t __percpu *crash_notes; -/* vmcoreinfo stuff */ -unsigned char *vmcoreinfo_data; -size_t vmcoreinfo_size; -u32 *vmcoreinfo_note; - -/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ -static unsigned char *vmcoreinfo_data_safecopy; - -/* Location of the reserved area for the crash kernel */ -struct resource crashk_res = { - .name = "Crash kernel", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, - .desc = IORES_DESC_CRASH_KERNEL -}; -struct resource crashk_low_res = { - .name = "Crash kernel", - .start = 0, - .end = 0, - .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, - .desc = IORES_DESC_CRASH_KERNEL -}; - -/* - * parsing the "crashkernel" commandline - * - * this code is intended to be called from architecture specific code - */ +#ifdef CONFIG_CRASH_DUMP - -/* - * This function parses command lines in the format - * - * crashkernel=ramsize-range:size[,...][@offset] - * - * The function returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_mem(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base) +int kimage_crash_copy_vmcoreinfo(struct kimage *image) { - char *cur = cmdline, *tmp; - unsigned long long total_mem = system_ram; + struct page *vmcoreinfo_page; + void *safecopy; + + if (!IS_ENABLED(CONFIG_CRASH_DUMP)) + return 0; + if (image->type != KEXEC_TYPE_CRASH) + return 0; /* - * Firmware sometimes reserves some memory regions for its own use, - * so the system memory size is less than the actual physical memory - * size. Work around this by rounding up the total size to 128M, - * which is enough for most test cases. + * For kdump, allocate one vmcoreinfo safe copy from the + * crash memory. as we have arch_kexec_protect_crashkres() + * after kexec syscall, we naturally protect it from write + * (even read) access under kernel direct mapping. But on + * the other hand, we still need to operate it when crash + * happens to generate vmcoreinfo note, hereby we rely on + * vmap for this purpose. */ - total_mem = roundup(total_mem, SZ_128M); - - /* for each entry of the comma-separated list */ - do { - unsigned long long start, end = ULLONG_MAX, size; - - /* get the start of the range */ - start = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("crashkernel: Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (*cur != '-') { - pr_warn("crashkernel: '-' expected\n"); - return -EINVAL; - } - cur++; - - /* if no ':' is here, than we read the end */ - if (*cur != ':') { - end = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("crashkernel: Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (end <= start) { - pr_warn("crashkernel: end <= start\n"); - return -EINVAL; - } - } - - if (*cur != ':') { - pr_warn("crashkernel: ':' expected\n"); - return -EINVAL; - } - cur++; - - size = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("Memory value expected\n"); - return -EINVAL; - } - cur = tmp; - if (size >= total_mem) { - pr_warn("crashkernel: invalid size\n"); - return -EINVAL; - } - - /* match ? */ - if (total_mem >= start && total_mem < end) { - *crash_size = size; - break; - } - } while (*cur++ == ','); - - if (*crash_size > 0) { - while (*cur && *cur != ' ' && *cur != '@') - cur++; - if (*cur == '@') { - cur++; - *crash_base = memparse(cur, &tmp); - if (cur == tmp) { - pr_warn("Memory value expected after '@'\n"); - return -EINVAL; - } - } - } else - pr_info("crashkernel size resulted in zero bytes\n"); - - return 0; -} - -/* - * That function parses "simple" (old) crashkernel command lines like - * - * crashkernel=size[@offset] - * - * It returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_simple(char *cmdline, - unsigned long long *crash_size, - unsigned long long *crash_base) -{ - char *cur = cmdline; - - *crash_size = memparse(cmdline, &cur); - if (cmdline == cur) { - pr_warn("crashkernel: memory value expected\n"); - return -EINVAL; - } - - if (*cur == '@') - *crash_base = memparse(cur+1, &cur); - else if (*cur != ' ' && *cur != '\0') { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; + vmcoreinfo_page = kimage_alloc_control_pages(image, 0); + if (!vmcoreinfo_page) { + pr_warn("Could not allocate vmcoreinfo buffer\n"); + return -ENOMEM; } - - return 0; -} - -#define SUFFIX_HIGH 0 -#define SUFFIX_LOW 1 -#define SUFFIX_NULL 2 -static __initdata char *suffix_tbl[] = { - [SUFFIX_HIGH] = ",high", - [SUFFIX_LOW] = ",low", - [SUFFIX_NULL] = NULL, -}; - -/* - * That function parses "suffix" crashkernel command lines like - * - * crashkernel=size,[high|low] - * - * It returns 0 on success and -EINVAL on failure. - */ -static int __init parse_crashkernel_suffix(char *cmdline, - unsigned long long *crash_size, - const char *suffix) -{ - char *cur = cmdline; - - *crash_size = memparse(cmdline, &cur); - if (cmdline == cur) { - pr_warn("crashkernel: memory value expected\n"); - return -EINVAL; + safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL); + if (!safecopy) { + pr_warn("Could not vmap vmcoreinfo buffer\n"); + return -ENOMEM; } - /* check with suffix */ - if (strncmp(cur, suffix, strlen(suffix))) { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; - } - cur += strlen(suffix); - if (*cur != ' ' && *cur != '\0') { - pr_warn("crashkernel: unrecognized char: %c\n", *cur); - return -EINVAL; - } + image->vmcoreinfo_data_copy = safecopy; + crash_update_vmcoreinfo_safecopy(safecopy); return 0; } -static __init char *get_last_crashkernel(char *cmdline, - const char *name, - const char *suffix) -{ - char *p = cmdline, *ck_cmdline = NULL; - - /* find crashkernel and use the last one if there are more */ - p = strstr(p, name); - while (p) { - char *end_p = strchr(p, ' '); - char *q; - - if (!end_p) - end_p = p + strlen(p); - - if (!suffix) { - int i; - - /* skip the one with any known suffix */ - for (i = 0; suffix_tbl[i]; i++) { - q = end_p - strlen(suffix_tbl[i]); - if (!strncmp(q, suffix_tbl[i], - strlen(suffix_tbl[i]))) - goto next; - } - ck_cmdline = p; - } else { - q = end_p - strlen(suffix); - if (!strncmp(q, suffix, strlen(suffix))) - ck_cmdline = p; - } -next: - p = strstr(p+1, name); - } - return ck_cmdline; -} -static int __init __parse_crashkernel(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base, - const char *suffix) +int kexec_should_crash(struct task_struct *p) { - char *first_colon, *first_space; - char *ck_cmdline; - char *name = "crashkernel="; - - BUG_ON(!crash_size || !crash_base); - *crash_size = 0; - *crash_base = 0; - - ck_cmdline = get_last_crashkernel(cmdline, name, suffix); - if (!ck_cmdline) - return -ENOENT; - - ck_cmdline += strlen(name); - - if (suffix) - return parse_crashkernel_suffix(ck_cmdline, crash_size, - suffix); /* - * if the commandline contains a ':', then that's the extended - * syntax -- if not, it must be the classic syntax + * If crash_kexec_post_notifiers is enabled, don't run + * crash_kexec() here yet, which must be run after panic + * notifiers in panic(). */ - first_colon = strchr(ck_cmdline, ':'); - first_space = strchr(ck_cmdline, ' '); - if (first_colon && (!first_space || first_colon < first_space)) - return parse_crashkernel_mem(ck_cmdline, system_ram, - crash_size, crash_base); - - return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base); -} - -/* - * That function is the entry point for command line parsing and should be - * called from the arch-specific code. - * - * If crashkernel=,high|low is supported on architecture, non-NULL values - * should be passed to parameters 'low_size' and 'high'. - */ -int __init parse_crashkernel(char *cmdline, - unsigned long long system_ram, - unsigned long long *crash_size, - unsigned long long *crash_base, - unsigned long long *low_size, - bool *high) -{ - int ret; - - /* crashkernel=X[@offset] */ - ret = __parse_crashkernel(cmdline, system_ram, crash_size, - crash_base, NULL); -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION + if (crash_kexec_post_notifiers) + return 0; /* - * If non-NULL 'high' passed in and no normal crashkernel - * setting detected, try parsing crashkernel=,high|low. + * There are 4 panic() calls in make_task_dead() path, each of which + * corresponds to each of these 4 conditions. */ - if (high && ret == -ENOENT) { - ret = __parse_crashkernel(cmdline, 0, crash_size, - crash_base, suffix_tbl[SUFFIX_HIGH]); - if (ret || !*crash_size) - return -EINVAL; - - /* - * crashkernel=Y,low can be specified or not, but invalid value - * is not allowed. - */ - ret = __parse_crashkernel(cmdline, 0, low_size, - crash_base, suffix_tbl[SUFFIX_LOW]); - if (ret == -ENOENT) { - *low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; - ret = 0; - } else if (ret) { - return ret; - } - - *high = true; - } -#endif - if (!*crash_size) - ret = -EINVAL; - - return ret; + if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) + return 1; + return 0; } -/* - * Add a dummy early_param handler to mark crashkernel= as a known command line - * parameter and suppress incorrect warnings in init/main.c. - */ -static int __init parse_crashkernel_dummy(char *arg) +int kexec_crash_loaded(void) { - return 0; + return !!kexec_crash_image; } -early_param("crashkernel", parse_crashkernel_dummy); +EXPORT_SYMBOL_GPL(kexec_crash_loaded); -#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION -static int __init reserve_crashkernel_low(unsigned long long low_size) +/* + * No panic_cpu check version of crash_kexec(). This function is called + * only when panic_cpu holds the current CPU number; this is the only CPU + * which processes crash_kexec routines. + */ +void __noclone __crash_kexec(struct pt_regs *regs) { -#ifdef CONFIG_64BIT - unsigned long long low_base; - - low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX); - if (!low_base) { - pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); - return -ENOMEM; + /* Take the kexec_lock here to prevent sys_kexec_load + * running on one cpu from replacing the crash kernel + * we are using after a panic on a different cpu. + * + * If the crash kernel was not located in a fixed area + * of memory the xchg(&kexec_crash_image) would be + * sufficient. But since I reuse the memory... + */ + if (kexec_trylock()) { + if (kexec_crash_image) { + struct pt_regs fixed_regs; + + crash_setup_regs(&fixed_regs, regs); + crash_save_vmcoreinfo(); + machine_crash_shutdown(&fixed_regs); + machine_kexec(kexec_crash_image); + } + kexec_unlock(); } - - pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n", - low_base, low_base + low_size, low_size >> 20); - - crashk_low_res.start = low_base; - crashk_low_res.end = low_base + low_size - 1; -#endif - return 0; } +STACK_FRAME_NON_STANDARD(__crash_kexec); -void __init reserve_crashkernel_generic(char *cmdline, - unsigned long long crash_size, - unsigned long long crash_base, - unsigned long long crash_low_size, - bool high) +__bpf_kfunc void crash_kexec(struct pt_regs *regs) { - unsigned long long search_end = CRASH_ADDR_LOW_MAX, search_base = 0; - bool fixed_base = false; - - /* User specifies base address explicitly. */ - if (crash_base) { - fixed_base = true; - search_base = crash_base; - search_end = crash_base + crash_size; - } else if (high) { - search_base = CRASH_ADDR_LOW_MAX; - search_end = CRASH_ADDR_HIGH_MAX; - } + int old_cpu, this_cpu; -retry: - crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, - search_base, search_end); - if (!crash_base) { - /* - * For crashkernel=size[KMG]@offset[KMG], print out failure - * message if can't reserve the specified region. - */ - if (fixed_base) { - pr_warn("crashkernel reservation failed - memory is in use.\n"); - return; - } + /* + * Only one CPU is allowed to execute the crash_kexec() code as with + * panic(). Otherwise parallel calls of panic() and crash_kexec() + * may stop each other. To exclude them, we use panic_cpu here too. + */ + old_cpu = PANIC_CPU_INVALID; + this_cpu = raw_smp_processor_id(); - /* - * For crashkernel=size[KMG], if the first attempt was for - * low memory, fall back to high memory, the minimum required - * low memory will be reserved later. - */ - if (!high && search_end == CRASH_ADDR_LOW_MAX) { - search_end = CRASH_ADDR_HIGH_MAX; - search_base = CRASH_ADDR_LOW_MAX; - crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; - goto retry; - } + if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) { + /* This is the 1st CPU which comes here, so go ahead. */ + __crash_kexec(regs); /* - * For crashkernel=size[KMG],high, if the first attempt was - * for high memory, fall back to low memory. + * Reset panic_cpu to allow another panic()/crash_kexec() + * call. */ - if (high && search_end == CRASH_ADDR_HIGH_MAX) { - search_end = CRASH_ADDR_LOW_MAX; - search_base = 0; - goto retry; - } - pr_warn("cannot allocate crashkernel (size:0x%llx)\n", - crash_size); - return; - } - - if ((crash_base >= CRASH_ADDR_LOW_MAX) && - crash_low_size && reserve_crashkernel_low(crash_low_size)) { - memblock_phys_free(crash_base, crash_size); - return; + atomic_set(&panic_cpu, PANIC_CPU_INVALID); } - - pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", - crash_base, crash_base + crash_size, crash_size >> 20); - - /* - * The crashkernel memory will be removed from the kernel linear - * map. Inform kmemleak so that it won't try to access it. - */ - kmemleak_ignore_phys(crash_base); - if (crashk_low_res.end) - kmemleak_ignore_phys(crashk_low_res.start); - - crashk_res.start = crash_base; - crashk_res.end = crash_base + crash_size - 1; } -static __init int insert_crashkernel_resources(void) +static inline resource_size_t crash_resource_size(const struct resource *res) { - if (crashk_res.start < crashk_res.end) - insert_resource(&iomem_resource, &crashk_res); + return !res->end ? 0 : resource_size(res); +} + - if (crashk_low_res.start < crashk_low_res.end) - insert_resource(&iomem_resource, &crashk_low_res); - return 0; -} -early_initcall(insert_crashkernel_resources); -#endif int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map, void **addr, unsigned long *sz) @@ -633,205 +317,129 @@ int crash_exclude_mem_range(struct crash_mem *mem, return 0; } -Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, - void *data, size_t data_len) +ssize_t crash_get_memory_size(void) { - struct elf_note *note = (struct elf_note *)buf; - - note->n_namesz = strlen(name) + 1; - note->n_descsz = data_len; - note->n_type = type; - buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word)); - memcpy(buf, name, note->n_namesz); - buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word)); - memcpy(buf, data, data_len); - buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word)); - - return buf; -} + ssize_t size = 0; -void final_note(Elf_Word *buf) -{ - memset(buf, 0, sizeof(struct elf_note)); -} + if (!kexec_trylock()) + return -EBUSY; -static void update_vmcoreinfo_note(void) -{ - u32 *buf = vmcoreinfo_note; + size += crash_resource_size(&crashk_res); + size += crash_resource_size(&crashk_low_res); - if (!vmcoreinfo_size) - return; - buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, - vmcoreinfo_size); - final_note(buf); + kexec_unlock(); + return size; } -void crash_update_vmcoreinfo_safecopy(void *ptr) +static int __crash_shrink_memory(struct resource *old_res, + unsigned long new_size) { - if (ptr) - memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size); + struct resource *ram_res; - vmcoreinfo_data_safecopy = ptr; -} + ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL); + if (!ram_res) + return -ENOMEM; -void crash_save_vmcoreinfo(void) -{ - if (!vmcoreinfo_note) - return; + ram_res->start = old_res->start + new_size; + ram_res->end = old_res->end; + ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; + ram_res->name = "System RAM"; + + if (!new_size) { + release_resource(old_res); + old_res->start = 0; + old_res->end = 0; + } else { + crashk_res.end = ram_res->start - 1; + } - /* Use the safe copy to generate vmcoreinfo note if have */ - if (vmcoreinfo_data_safecopy) - vmcoreinfo_data = vmcoreinfo_data_safecopy; + crash_free_reserved_phys_range(ram_res->start, ram_res->end); + insert_resource(&iomem_resource, ram_res); - vmcoreinfo_append_str("CRASHTIME=%lld\n", ktime_get_real_seconds()); - update_vmcoreinfo_note(); + return 0; } -void vmcoreinfo_append_str(const char *fmt, ...) +int crash_shrink_memory(unsigned long new_size) { - va_list args; - char buf[0x50]; - size_t r; - - va_start(args, fmt); - r = vscnprintf(buf, sizeof(buf), fmt, args); - va_end(args); - - r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size); - - memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); - - vmcoreinfo_size += r; - - WARN_ONCE(vmcoreinfo_size == VMCOREINFO_BYTES, - "vmcoreinfo data exceeds allocated size, truncating"); -} + int ret = 0; + unsigned long old_size, low_size; -/* - * provide an empty default implementation here -- architecture - * code may override this - */ -void __weak arch_crash_save_vmcoreinfo(void) -{} + if (!kexec_trylock()) + return -EBUSY; -phys_addr_t __weak paddr_vmcoreinfo_note(void) -{ - return __pa(vmcoreinfo_note); -} -EXPORT_SYMBOL(paddr_vmcoreinfo_note); + if (kexec_crash_image) { + ret = -ENOENT; + goto unlock; + } -static int __init crash_save_vmcoreinfo_init(void) -{ - vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); - if (!vmcoreinfo_data) { - pr_warn("Memory allocation for vmcoreinfo_data failed\n"); - return -ENOMEM; + low_size = crash_resource_size(&crashk_low_res); + old_size = crash_resource_size(&crashk_res) + low_size; + new_size = roundup(new_size, KEXEC_CRASH_MEM_ALIGN); + if (new_size >= old_size) { + ret = (new_size == old_size) ? 0 : -EINVAL; + goto unlock; } - vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE, - GFP_KERNEL | __GFP_ZERO); - if (!vmcoreinfo_note) { - free_page((unsigned long)vmcoreinfo_data); - vmcoreinfo_data = NULL; - pr_warn("Memory allocation for vmcoreinfo_note failed\n"); - return -ENOMEM; + /* + * (low_size > new_size) implies that low_size is greater than zero. + * This also means that if low_size is zero, the else branch is taken. + * + * If low_size is greater than 0, (low_size > new_size) indicates that + * crashk_low_res also needs to be shrunken. Otherwise, only crashk_res + * needs to be shrunken. + */ + if (low_size > new_size) { + ret = __crash_shrink_memory(&crashk_res, 0); + if (ret) + goto unlock; + + ret = __crash_shrink_memory(&crashk_low_res, new_size); + } else { + ret = __crash_shrink_memory(&crashk_res, new_size - low_size); } - VMCOREINFO_OSRELEASE(init_uts_ns.name.release); - VMCOREINFO_BUILD_ID(); - VMCOREINFO_PAGESIZE(PAGE_SIZE); + /* Swap crashk_res and crashk_low_res if needed */ + if (!crashk_res.end && crashk_low_res.end) { + crashk_res.start = crashk_low_res.start; + crashk_res.end = crashk_low_res.end; + release_resource(&crashk_low_res); + crashk_low_res.start = 0; + crashk_low_res.end = 0; + insert_resource(&iomem_resource, &crashk_res); + } - VMCOREINFO_SYMBOL(init_uts_ns); - VMCOREINFO_OFFSET(uts_namespace, name); - VMCOREINFO_SYMBOL(node_online_map); -#ifdef CONFIG_MMU - VMCOREINFO_SYMBOL_ARRAY(swapper_pg_dir); -#endif - VMCOREINFO_SYMBOL(_stext); - VMCOREINFO_SYMBOL(vmap_area_list); +unlock: + kexec_unlock(); + return ret; +} -#ifndef CONFIG_NUMA - VMCOREINFO_SYMBOL(mem_map); - VMCOREINFO_SYMBOL(contig_page_data); -#endif -#ifdef CONFIG_SPARSEMEM - VMCOREINFO_SYMBOL_ARRAY(mem_section); - VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); - VMCOREINFO_STRUCT_SIZE(mem_section); - VMCOREINFO_OFFSET(mem_section, section_mem_map); - VMCOREINFO_NUMBER(SECTION_SIZE_BITS); - VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); -#endif - VMCOREINFO_STRUCT_SIZE(page); - VMCOREINFO_STRUCT_SIZE(pglist_data); - VMCOREINFO_STRUCT_SIZE(zone); - VMCOREINFO_STRUCT_SIZE(free_area); - VMCOREINFO_STRUCT_SIZE(list_head); - VMCOREINFO_SIZE(nodemask_t); - VMCOREINFO_OFFSET(page, flags); - VMCOREINFO_OFFSET(page, _refcount); - VMCOREINFO_OFFSET(page, mapping); - VMCOREINFO_OFFSET(page, lru); - VMCOREINFO_OFFSET(page, _mapcount); - VMCOREINFO_OFFSET(page, private); - VMCOREINFO_OFFSET(page, compound_head); - VMCOREINFO_OFFSET(pglist_data, node_zones); - VMCOREINFO_OFFSET(pglist_data, nr_zones); -#ifdef CONFIG_FLATMEM - VMCOREINFO_OFFSET(pglist_data, node_mem_map); -#endif - VMCOREINFO_OFFSET(pglist_data, node_start_pfn); - VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); - VMCOREINFO_OFFSET(pglist_data, node_id); - VMCOREINFO_OFFSET(zone, free_area); - VMCOREINFO_OFFSET(zone, vm_stat); - VMCOREINFO_OFFSET(zone, spanned_pages); - VMCOREINFO_OFFSET(free_area, free_list); - VMCOREINFO_OFFSET(list_head, next); - VMCOREINFO_OFFSET(list_head, prev); - VMCOREINFO_OFFSET(vmap_area, va_start); - VMCOREINFO_OFFSET(vmap_area, list); - VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS); - log_buf_vmcoreinfo_setup(); - VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); - VMCOREINFO_NUMBER(NR_FREE_PAGES); - VMCOREINFO_NUMBER(PG_lru); - VMCOREINFO_NUMBER(PG_private); - VMCOREINFO_NUMBER(PG_swapcache); - VMCOREINFO_NUMBER(PG_swapbacked); - VMCOREINFO_NUMBER(PG_slab); -#ifdef CONFIG_MEMORY_FAILURE - VMCOREINFO_NUMBER(PG_hwpoison); -#endif - VMCOREINFO_NUMBER(PG_head_mask); -#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) - VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); -#ifdef CONFIG_HUGETLB_PAGE - VMCOREINFO_NUMBER(PG_hugetlb); -#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) - VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); -#endif +void crash_save_cpu(struct pt_regs *regs, int cpu) +{ + struct elf_prstatus prstatus; + u32 *buf; -#ifdef CONFIG_KALLSYMS - VMCOREINFO_SYMBOL(kallsyms_names); - VMCOREINFO_SYMBOL(kallsyms_num_syms); - VMCOREINFO_SYMBOL(kallsyms_token_table); - VMCOREINFO_SYMBOL(kallsyms_token_index); -#ifdef CONFIG_KALLSYMS_BASE_RELATIVE - VMCOREINFO_SYMBOL(kallsyms_offsets); - VMCOREINFO_SYMBOL(kallsyms_relative_base); -#else - VMCOREINFO_SYMBOL(kallsyms_addresses); -#endif /* CONFIG_KALLSYMS_BASE_RELATIVE */ -#endif /* CONFIG_KALLSYMS */ - - arch_crash_save_vmcoreinfo(); - update_vmcoreinfo_note(); + if ((cpu < 0) || (cpu >= nr_cpu_ids)) + return; - return 0; + /* Using ELF notes here is opportunistic. + * I need a well defined structure format + * for the data I pass, and I need tags + * on the data to indicate what information I have + * squirrelled away. ELF notes happen to provide + * all of that, so there is no need to invent something new. + */ + buf = (u32 *)per_cpu_ptr(crash_notes, cpu); + if (!buf) + return; + memset(&prstatus, 0, sizeof(prstatus)); + prstatus.common.pr_pid = current->pid; + elf_core_copy_regs(&prstatus.pr_reg, regs); + buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, + &prstatus, sizeof(prstatus)); + final_note(buf); } -subsys_initcall(crash_save_vmcoreinfo_init); + static int __init crash_notes_memory_init(void) { @@ -866,6 +474,8 @@ static int __init crash_notes_memory_init(void) } subsys_initcall(crash_notes_memory_init); +#endif /*CONFIG_CRASH_DUMP*/ + #ifdef CONFIG_CRASH_HOTPLUG #undef pr_fmt #define pr_fmt(fmt) "crash hp: " fmt diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c new file mode 100644 index 000000000000..bbb6c3cb00e4 --- /dev/null +++ b/kernel/crash_reserve.c @@ -0,0 +1,464 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * crash.c - kernel crash support code. + * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> + */ + +#include <linux/buildid.h> +#include <linux/init.h> +#include <linux/utsname.h> +#include <linux/vmalloc.h> +#include <linux/sizes.h> +#include <linux/kexec.h> +#include <linux/memory.h> +#include <linux/cpuhotplug.h> +#include <linux/memblock.h> +#include <linux/kexec.h> +#include <linux/kmemleak.h> + +#include <asm/page.h> +#include <asm/sections.h> + +#include <crypto/sha1.h> + +#include "kallsyms_internal.h" +#include "kexec_internal.h" + +/* Location of the reserved area for the crash kernel */ +struct resource crashk_res = { + .name = "Crash kernel", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL +}; +struct resource crashk_low_res = { + .name = "Crash kernel", + .start = 0, + .end = 0, + .flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM, + .desc = IORES_DESC_CRASH_KERNEL +}; + +/* + * parsing the "crashkernel" commandline + * + * this code is intended to be called from architecture specific code + */ + + +/* + * This function parses command lines in the format + * + * crashkernel=ramsize-range:size[,...][@offset] + * + * The function returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_mem(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline, *tmp; + unsigned long long total_mem = system_ram; + + /* + * Firmware sometimes reserves some memory regions for its own use, + * so the system memory size is less than the actual physical memory + * size. Work around this by rounding up the total size to 128M, + * which is enough for most test cases. + */ + total_mem = roundup(total_mem, SZ_128M); + + /* for each entry of the comma-separated list */ + do { + unsigned long long start, end = ULLONG_MAX, size; + + /* get the start of the range */ + start = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (*cur != '-') { + pr_warn("crashkernel: '-' expected\n"); + return -EINVAL; + } + cur++; + + /* if no ':' is here, than we read the end */ + if (*cur != ':') { + end = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("crashkernel: Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (end <= start) { + pr_warn("crashkernel: end <= start\n"); + return -EINVAL; + } + } + + if (*cur != ':') { + pr_warn("crashkernel: ':' expected\n"); + return -EINVAL; + } + cur++; + + size = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("Memory value expected\n"); + return -EINVAL; + } + cur = tmp; + if (size >= total_mem) { + pr_warn("crashkernel: invalid size\n"); + return -EINVAL; + } + + /* match ? */ + if (total_mem >= start && total_mem < end) { + *crash_size = size; + break; + } + } while (*cur++ == ','); + + if (*crash_size > 0) { + while (*cur && *cur != ' ' && *cur != '@') + cur++; + if (*cur == '@') { + cur++; + *crash_base = memparse(cur, &tmp); + if (cur == tmp) { + pr_warn("Memory value expected after '@'\n"); + return -EINVAL; + } + } + } else + pr_info("crashkernel size resulted in zero bytes\n"); + + return 0; +} + +/* + * That function parses "simple" (old) crashkernel command lines like + * + * crashkernel=size[@offset] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_simple(char *cmdline, + unsigned long long *crash_size, + unsigned long long *crash_base) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + if (*cur == '@') + *crash_base = memparse(cur+1, &cur); + else if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + + return 0; +} + +#define SUFFIX_HIGH 0 +#define SUFFIX_LOW 1 +#define SUFFIX_NULL 2 +static __initdata char *suffix_tbl[] = { + [SUFFIX_HIGH] = ",high", + [SUFFIX_LOW] = ",low", + [SUFFIX_NULL] = NULL, +}; + +/* + * That function parses "suffix" crashkernel command lines like + * + * crashkernel=size,[high|low] + * + * It returns 0 on success and -EINVAL on failure. + */ +static int __init parse_crashkernel_suffix(char *cmdline, + unsigned long long *crash_size, + const char *suffix) +{ + char *cur = cmdline; + + *crash_size = memparse(cmdline, &cur); + if (cmdline == cur) { + pr_warn("crashkernel: memory value expected\n"); + return -EINVAL; + } + + /* check with suffix */ + if (strncmp(cur, suffix, strlen(suffix))) { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + cur += strlen(suffix); + if (*cur != ' ' && *cur != '\0') { + pr_warn("crashkernel: unrecognized char: %c\n", *cur); + return -EINVAL; + } + + return 0; +} + +static __init char *get_last_crashkernel(char *cmdline, + const char *name, + const char *suffix) +{ + char *p = cmdline, *ck_cmdline = NULL; + + /* find crashkernel and use the last one if there are more */ + p = strstr(p, name); + while (p) { + char *end_p = strchr(p, ' '); + char *q; + + if (!end_p) + end_p = p + strlen(p); + + if (!suffix) { + int i; + + /* skip the one with any known suffix */ + for (i = 0; suffix_tbl[i]; i++) { + q = end_p - strlen(suffix_tbl[i]); + if (!strncmp(q, suffix_tbl[i], + strlen(suffix_tbl[i]))) + goto next; + } + ck_cmdline = p; + } else { + q = end_p - strlen(suffix); + if (!strncmp(q, suffix, strlen(suffix))) + ck_cmdline = p; + } +next: + p = strstr(p+1, name); + } + + return ck_cmdline; +} + +static int __init __parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base, + const char *suffix) +{ + char *first_colon, *first_space; + char *ck_cmdline; + char *name = "crashkernel="; + + BUG_ON(!crash_size || !crash_base); + *crash_size = 0; + *crash_base = 0; + + ck_cmdline = get_last_crashkernel(cmdline, name, suffix); + if (!ck_cmdline) + return -ENOENT; + + ck_cmdline += strlen(name); + + if (suffix) + return parse_crashkernel_suffix(ck_cmdline, crash_size, + suffix); + /* + * if the commandline contains a ':', then that's the extended + * syntax -- if not, it must be the classic syntax + */ + first_colon = strchr(ck_cmdline, ':'); + first_space = strchr(ck_cmdline, ' '); + if (first_colon && (!first_space || first_colon < first_space)) + return parse_crashkernel_mem(ck_cmdline, system_ram, + crash_size, crash_base); + + return parse_crashkernel_simple(ck_cmdline, crash_size, crash_base); +} + +/* + * That function is the entry point for command line parsing and should be + * called from the arch-specific code. + * + * If crashkernel=,high|low is supported on architecture, non-NULL values + * should be passed to parameters 'low_size' and 'high'. + */ +int __init parse_crashkernel(char *cmdline, + unsigned long long system_ram, + unsigned long long *crash_size, + unsigned long long *crash_base, + unsigned long long *low_size, + bool *high) +{ + int ret; + + /* crashkernel=X[@offset] */ + ret = __parse_crashkernel(cmdline, system_ram, crash_size, + crash_base, NULL); +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION + /* + * If non-NULL 'high' passed in and no normal crashkernel + * setting detected, try parsing crashkernel=,high|low. + */ + if (high && ret == -ENOENT) { + ret = __parse_crashkernel(cmdline, 0, crash_size, + crash_base, suffix_tbl[SUFFIX_HIGH]); + if (ret || !*crash_size) + return -EINVAL; + + /* + * crashkernel=Y,low can be specified or not, but invalid value + * is not allowed. + */ + ret = __parse_crashkernel(cmdline, 0, low_size, + crash_base, suffix_tbl[SUFFIX_LOW]); + if (ret == -ENOENT) { + *low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + ret = 0; + } else if (ret) { + return ret; + } + + *high = true; + } +#endif + if (!*crash_size) + ret = -EINVAL; + + return ret; +} + +/* + * Add a dummy early_param handler to mark crashkernel= as a known command line + * parameter and suppress incorrect warnings in init/main.c. + */ +static int __init parse_crashkernel_dummy(char *arg) +{ + return 0; +} +early_param("crashkernel", parse_crashkernel_dummy); + +#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION +static int __init reserve_crashkernel_low(unsigned long long low_size) +{ +#ifdef CONFIG_64BIT + unsigned long long low_base; + + low_base = memblock_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX); + if (!low_base) { + pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size); + return -ENOMEM; + } + + pr_info("crashkernel low memory reserved: 0x%08llx - 0x%08llx (%lld MB)\n", + low_base, low_base + low_size, low_size >> 20); + + crashk_low_res.start = low_base; + crashk_low_res.end = low_base + low_size - 1; + insert_resource(&iomem_resource, &crashk_low_res); +#endif + return 0; +} + +void __init reserve_crashkernel_generic(char *cmdline, + unsigned long long crash_size, + unsigned long long crash_base, + unsigned long long crash_low_size, + bool high) +{ + unsigned long long search_end = CRASH_ADDR_LOW_MAX, search_base = 0; + bool fixed_base = false; + + /* User specifies base address explicitly. */ + if (crash_base) { + fixed_base = true; + search_base = crash_base; + search_end = crash_base + crash_size; + } else if (high) { + search_base = CRASH_ADDR_LOW_MAX; + search_end = CRASH_ADDR_HIGH_MAX; + } + +retry: + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, + search_base, search_end); + if (!crash_base) { + /* + * For crashkernel=size[KMG]@offset[KMG], print out failure + * message if can't reserve the specified region. + */ + if (fixed_base) { + pr_warn("crashkernel reservation failed - memory is in use.\n"); + return; + } + + /* + * For crashkernel=size[KMG], if the first attempt was for + * low memory, fall back to high memory, the minimum required + * low memory will be reserved later. + */ + if (!high && search_end == CRASH_ADDR_LOW_MAX) { + search_end = CRASH_ADDR_HIGH_MAX; + search_base = CRASH_ADDR_LOW_MAX; + crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE; + goto retry; + } + + /* + * For crashkernel=size[KMG],high, if the first attempt was + * for high memory, fall back to low memory. + */ + if (high && search_end == CRASH_ADDR_HIGH_MAX) { + search_end = CRASH_ADDR_LOW_MAX; + search_base = 0; + goto retry; + } + pr_warn("cannot allocate crashkernel (size:0x%llx)\n", + crash_size); + return; + } + + if ((crash_base >= CRASH_ADDR_LOW_MAX) && + crash_low_size && reserve_crashkernel_low(crash_low_size)) { + memblock_phys_free(crash_base, crash_size); + return; + } + + pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n", + crash_base, crash_base + crash_size, crash_size >> 20); + + /* + * The crashkernel memory will be removed from the kernel linear + * map. Inform kmemleak so that it won't try to access it. + */ + kmemleak_ignore_phys(crash_base); + if (crashk_low_res.end) + kmemleak_ignore_phys(crashk_low_res.start); + + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; +} + +static __init int insert_crashkernel_resources(void) +{ + if (crashk_res.start < crashk_res.end) + insert_resource(&iomem_resource, &crashk_res); + + if (crashk_low_res.start < crashk_low_res.end) + insert_resource(&iomem_resource, &crashk_low_res); + + return 0; +} +early_initcall(insert_crashkernel_resources); +#endif diff --git a/kernel/cred.c b/kernel/cred.c index c033a201c808..075cfa7c896f 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -606,8 +606,8 @@ int set_cred_ucounts(struct cred *new) void __init cred_init(void) { /* allocate a slab in which we can store credentials */ - cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), 0, - SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); + cred_jar = KMEM_CACHE(cred, + SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT); } /** diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c index f005c66f378c..055da410ac71 100644 --- a/kernel/dma/contiguous.c +++ b/kernel/dma/contiguous.c @@ -37,12 +37,6 @@ #define pr_fmt(fmt) "cma: " fmt -#ifdef CONFIG_CMA_DEBUG -#ifndef DEBUG -# define DEBUG -#endif -#endif - #include <asm/page.h> #include <linux/memblock.h> diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index 98b2e192fd69..4d543b1e9d57 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -286,7 +286,7 @@ void *dma_direct_alloc(struct device *dev, size_t size, } else { ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) - goto out_free_pages; + goto out_leak_pages; } memset(ret, 0, size); @@ -307,6 +307,8 @@ out_encrypt_pages: out_free_pages: __dma_direct_free_pages(dev, page, size); return NULL; +out_leak_pages: + return NULL; } void dma_direct_free(struct device *dev, size_t size, @@ -367,12 +369,11 @@ struct page *dma_direct_alloc_pages(struct device *dev, size_t size, ret = page_address(page); if (dma_set_decrypted(dev, ret, size)) - goto out_free_pages; + goto out_leak_pages; memset(ret, 0, size); *dma_handle = phys_to_dma_direct(dev, page_to_phys(page)); return page; -out_free_pages: - __dma_direct_free_pages(dev, page, size); +out_leak_pages: return NULL; } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index b079a9a8e087..77974cea3e69 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -956,6 +956,28 @@ static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) } #endif /* CONFIG_DEBUG_FS */ +#ifdef CONFIG_SWIOTLB_DYNAMIC +#ifdef CONFIG_DEBUG_FS +static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots) +{ + atomic_long_add(nslots, &mem->transient_nslabs); +} + +static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots) +{ + atomic_long_sub(nslots, &mem->transient_nslabs); +} + +#else /* !CONFIG_DEBUG_FS */ +static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots) +{ +} +static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots) +{ +} +#endif /* CONFIG_DEBUG_FS */ +#endif /* CONFIG_SWIOTLB_DYNAMIC */ + /** * swiotlb_search_pool_area() - search one memory area in one pool * @dev: Device which maps the buffer. @@ -1170,6 +1192,7 @@ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, spin_lock_irqsave(&dev->dma_io_tlb_lock, flags); list_add_rcu(&pool->node, &dev->dma_io_tlb_pools); spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); + inc_transient_used(mem, pool->nslabs); found: WRITE_ONCE(dev->dma_uses_io_tlb, true); @@ -1415,6 +1438,7 @@ static bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr) dec_used(dev->dma_io_tlb_mem, pool->nslabs); swiotlb_del_pool(dev, pool); + dec_transient_used(dev->dma_io_tlb_mem, pool->nslabs); return true; } @@ -1557,6 +1581,23 @@ phys_addr_t default_swiotlb_limit(void) } #ifdef CONFIG_DEBUG_FS +#ifdef CONFIG_SWIOTLB_DYNAMIC +static unsigned long mem_transient_used(struct io_tlb_mem *mem) +{ + return atomic_long_read(&mem->transient_nslabs); +} + +static int io_tlb_transient_used_get(void *data, u64 *val) +{ + struct io_tlb_mem *mem = data; + + *val = mem_transient_used(mem); + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_transient_used, io_tlb_transient_used_get, + NULL, "%llu\n"); +#endif /* CONFIG_SWIOTLB_DYNAMIC */ static int io_tlb_used_get(void *data, u64 *val) { @@ -1605,6 +1646,11 @@ static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, &fops_io_tlb_used); debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem, &fops_io_tlb_hiwater); +#ifdef CONFIG_SWIOTLB_DYNAMIC + atomic_long_set(&mem->transient_nslabs, 0); + debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs, + mem, &fops_io_tlb_transient_used); +#endif } static int __init swiotlb_create_default_debugfs(void) diff --git a/kernel/crash_dump.c b/kernel/elfcorehdr.c index 92da32275af5..92da32275af5 100644 --- a/kernel/crash_dump.c +++ b/kernel/elfcorehdr.c diff --git a/kernel/events/core.c b/kernel/events/core.c index f0f0f71213a1..724e6d7e128f 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9302,10 +9302,6 @@ void perf_event_bpf_event(struct bpf_prog *prog, { struct perf_bpf_event bpf_event; - if (type <= PERF_BPF_EVENT_UNKNOWN || - type >= PERF_BPF_EVENT_MAX) - return; - switch (type) { case PERF_BPF_EVENT_PROG_LOAD: case PERF_BPF_EVENT_PROG_UNLOAD: @@ -9313,7 +9309,7 @@ void perf_event_bpf_event(struct bpf_prog *prog, perf_event_bpf_emit_ksymbols(prog, type); break; default: - break; + return; } if (!atomic_read(&nr_bpf_events)) @@ -10557,7 +10553,7 @@ int perf_event_set_bpf_prog(struct perf_event *event, struct bpf_prog *prog, (is_syscall_tp && prog->type != BPF_PROG_TYPE_TRACEPOINT)) return -EINVAL; - if (prog->type == BPF_PROG_TYPE_KPROBE && prog->aux->sleepable && !is_uprobe) + if (prog->type == BPF_PROG_TYPE_KPROBE && prog->sleepable && !is_uprobe) /* only uprobe programs are allowed to be sleepable */ return -EINVAL; diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c index 929e98c62965..e4834d23e1d1 100644 --- a/kernel/events/uprobes.c +++ b/kernel/events/uprobes.c @@ -188,7 +188,7 @@ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, dec_mm_counter(mm, MM_ANONPAGES); if (!folio_test_anon(old_folio)) { - dec_mm_counter(mm, mm_counter_file(old_page)); + dec_mm_counter(mm, mm_counter_file(old_folio)); inc_mm_counter(mm, MM_ANONPAGES); } diff --git a/kernel/exit.c b/kernel/exit.c index dfb963d2f862..41a12630cbbc 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -739,6 +739,13 @@ static void exit_notify(struct task_struct *tsk, int group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); tsk->exit_state = EXIT_ZOMBIE; + /* + * sub-thread or delay_group_leader(), wake up the + * PIDFD_THREAD waiters. + */ + if (!thread_group_empty(tsk)) + do_notify_pidfd(tsk); + if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && @@ -1889,30 +1896,6 @@ Efault: } #endif -/** - * thread_group_exited - check that a thread group has exited - * @pid: tgid of thread group to be checked. - * - * Test if the thread group represented by tgid has exited (all - * threads are zombies, dead or completely gone). - * - * Return: true if the thread group has exited. false otherwise. - */ -bool thread_group_exited(struct pid *pid) -{ - struct task_struct *task; - bool exited; - - rcu_read_lock(); - task = pid_task(pid, PIDTYPE_PID); - exited = !task || - (READ_ONCE(task->exit_state) && thread_group_empty(task)); - rcu_read_unlock(); - - return exited; -} -EXPORT_SYMBOL(thread_group_exited); - /* * This needs to be __function_aligned as GCC implicitly makes any * implementation of abort() cold and drops alignment specified by diff --git a/kernel/fork.c b/kernel/fork.c index 0d944e92a43f..39a5046c2f0b 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -101,6 +101,8 @@ #include <linux/user_events.h> #include <linux/iommu.h> #include <linux/rseq.h> +#include <uapi/linux/pidfd.h> +#include <linux/pidfs.h> #include <asm/pgalloc.h> #include <linux/uaccess.h> @@ -1976,6 +1978,7 @@ static inline void rcu_copy_process(struct task_struct *p) p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; + INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; @@ -1985,119 +1988,6 @@ static inline void rcu_copy_process(struct task_struct *p) #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } -struct pid *pidfd_pid(const struct file *file) -{ - if (file->f_op == &pidfd_fops) - return file->private_data; - - return ERR_PTR(-EBADF); -} - -static int pidfd_release(struct inode *inode, struct file *file) -{ - struct pid *pid = file->private_data; - - file->private_data = NULL; - put_pid(pid); - return 0; -} - -#ifdef CONFIG_PROC_FS -/** - * pidfd_show_fdinfo - print information about a pidfd - * @m: proc fdinfo file - * @f: file referencing a pidfd - * - * Pid: - * This function will print the pid that a given pidfd refers to in the - * pid namespace of the procfs instance. - * If the pid namespace of the process is not a descendant of the pid - * namespace of the procfs instance 0 will be shown as its pid. This is - * similar to calling getppid() on a process whose parent is outside of - * its pid namespace. - * - * NSpid: - * If pid namespaces are supported then this function will also print - * the pid of a given pidfd refers to for all descendant pid namespaces - * starting from the current pid namespace of the instance, i.e. the - * Pid field and the first entry in the NSpid field will be identical. - * If the pid namespace of the process is not a descendant of the pid - * namespace of the procfs instance 0 will be shown as its first NSpid - * entry and no others will be shown. - * Note that this differs from the Pid and NSpid fields in - * /proc/<pid>/status where Pid and NSpid are always shown relative to - * the pid namespace of the procfs instance. The difference becomes - * obvious when sending around a pidfd between pid namespaces from a - * different branch of the tree, i.e. where no ancestral relation is - * present between the pid namespaces: - * - create two new pid namespaces ns1 and ns2 in the initial pid - * namespace (also take care to create new mount namespaces in the - * new pid namespace and mount procfs) - * - create a process with a pidfd in ns1 - * - send pidfd from ns1 to ns2 - * - read /proc/self/fdinfo/<pidfd> and observe that both Pid and NSpid - * have exactly one entry, which is 0 - */ -static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) -{ - struct pid *pid = f->private_data; - struct pid_namespace *ns; - pid_t nr = -1; - - if (likely(pid_has_task(pid, PIDTYPE_PID))) { - ns = proc_pid_ns(file_inode(m->file)->i_sb); - nr = pid_nr_ns(pid, ns); - } - - seq_put_decimal_ll(m, "Pid:\t", nr); - -#ifdef CONFIG_PID_NS - seq_put_decimal_ll(m, "\nNSpid:\t", nr); - if (nr > 0) { - int i; - - /* If nr is non-zero it means that 'pid' is valid and that - * ns, i.e. the pid namespace associated with the procfs - * instance, is in the pid namespace hierarchy of pid. - * Start at one below the already printed level. - */ - for (i = ns->level + 1; i <= pid->level; i++) - seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); - } -#endif - seq_putc(m, '\n'); -} -#endif - -/* - * Poll support for process exit notification. - */ -static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) -{ - struct pid *pid = file->private_data; - __poll_t poll_flags = 0; - - poll_wait(file, &pid->wait_pidfd, pts); - - /* - * Inform pollers only when the whole thread group exits. - * If the thread group leader exits before all other threads in the - * group, then poll(2) should block, similar to the wait(2) family. - */ - if (thread_group_exited(pid)) - poll_flags = EPOLLIN | EPOLLRDNORM; - - return poll_flags; -} - -const struct file_operations pidfd_fops = { - .release = pidfd_release, - .poll = pidfd_poll, -#ifdef CONFIG_PROC_FS - .show_fdinfo = pidfd_show_fdinfo, -#endif -}; - /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd @@ -2131,20 +2021,20 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re int pidfd; struct file *pidfd_file; - if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) - return -EINVAL; - - pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + pidfd = get_unused_fd_flags(O_CLOEXEC); if (pidfd < 0) return pidfd; - pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, - flags | O_RDWR | O_CLOEXEC); + pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfd_file)) { put_unused_fd(pidfd); return PTR_ERR(pidfd_file); } - get_pid(pid); /* held by pidfd_file now */ + /* + * anon_inode_getfile() ignores everything outside of the + * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually. + */ + pidfd_file->f_flags |= (flags & PIDFD_THREAD); *ret = pidfd_file; return pidfd; } @@ -2158,7 +2048,8 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * - * The helper verifies that @pid is used as a thread group leader. + * The helper verifies that @pid is still in use, without PIDFD_THREAD the + * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in @@ -2177,7 +2068,9 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { - if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) + bool thread = flags & PIDFD_THREAD; + + if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) return -EINVAL; return __pidfd_prepare(pid, flags, ret); @@ -2299,9 +2192,8 @@ __latent_entropy struct task_struct *copy_process( /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. - * - CLONE_THREAD is blocked until someone really needs it. */ - if (clone_flags & (CLONE_DETACHED | CLONE_THREAD)) + if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } @@ -2524,8 +2416,10 @@ __latent_entropy struct task_struct *copy_process( * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { + int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; + /* Note that no task has been attached to @pid yet. */ - retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile); + retval = __pidfd_prepare(pid, flags, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; @@ -2876,8 +2770,8 @@ pid_t kernel_clone(struct kernel_clone_args *args) * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ - if ((args->flags & CLONE_PIDFD) && - (args->flags & CLONE_PARENT_SETTID) && + if ((clone_flags & CLONE_PIDFD) && + (clone_flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; diff --git a/kernel/hung_task.c b/kernel/hung_task.c index 9a24574988d2..b2fc2727d654 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -43,6 +43,7 @@ static int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; * Zero means infinite timeout - no checking done: */ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT; +EXPORT_SYMBOL_GPL(sysctl_hung_task_timeout_secs); /* * Zero (default value) means use sysctl_hung_task_timeout_secs: diff --git a/kernel/irq/irq_sim.c b/kernel/irq/irq_sim.c index dd76323ea3fd..38d6ae651ac7 100644 --- a/kernel/irq/irq_sim.c +++ b/kernel/irq/irq_sim.c @@ -4,10 +4,11 @@ * Copyright (C) 2020 Bartosz Golaszewski <bgolaszewski@baylibre.com> */ +#include <linux/cleanup.h> +#include <linux/interrupt.h> #include <linux/irq.h> #include <linux/irq_sim.h> #include <linux/irq_work.h> -#include <linux/interrupt.h> #include <linux/slab.h> struct irq_sim_work_ctx { @@ -19,7 +20,6 @@ struct irq_sim_work_ctx { }; struct irq_sim_irq_ctx { - int irqnum; bool enabled; struct irq_sim_work_ctx *work_ctx; }; @@ -164,33 +164,27 @@ static const struct irq_domain_ops irq_sim_domain_ops = { struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode, unsigned int num_irqs) { - struct irq_sim_work_ctx *work_ctx; + struct irq_sim_work_ctx *work_ctx __free(kfree) = + kmalloc(sizeof(*work_ctx), GFP_KERNEL); - work_ctx = kmalloc(sizeof(*work_ctx), GFP_KERNEL); if (!work_ctx) - goto err_out; + return ERR_PTR(-ENOMEM); - work_ctx->pending = bitmap_zalloc(num_irqs, GFP_KERNEL); - if (!work_ctx->pending) - goto err_free_work_ctx; + unsigned long *pending __free(bitmap) = bitmap_zalloc(num_irqs, GFP_KERNEL); + if (!pending) + return ERR_PTR(-ENOMEM); work_ctx->domain = irq_domain_create_linear(fwnode, num_irqs, &irq_sim_domain_ops, work_ctx); if (!work_ctx->domain) - goto err_free_bitmap; + return ERR_PTR(-ENOMEM); work_ctx->irq_count = num_irqs; work_ctx->work = IRQ_WORK_INIT_HARD(irq_sim_handle_irq); + work_ctx->pending = no_free_ptr(pending); - return work_ctx->domain; - -err_free_bitmap: - bitmap_free(work_ctx->pending); -err_free_work_ctx: - kfree(work_ctx); -err_out: - return ERR_PTR(-ENOMEM); + return no_free_ptr(work_ctx)->domain; } EXPORT_SYMBOL_GPL(irq_domain_create_sim); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index 371eb1711d34..4c6b32318ce3 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -92,11 +92,23 @@ static void desc_smp_init(struct irq_desc *desc, int node, #endif } +static void free_masks(struct irq_desc *desc) +{ +#ifdef CONFIG_GENERIC_PENDING_IRQ + free_cpumask_var(desc->pending_mask); +#endif + free_cpumask_var(desc->irq_common_data.affinity); +#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK + free_cpumask_var(desc->irq_common_data.effective_affinity); +#endif +} + #else static inline int alloc_masks(struct irq_desc *desc, int node) { return 0; } static inline void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { } +static inline void free_masks(struct irq_desc *desc) { } #endif static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, @@ -166,6 +178,39 @@ static void delete_irq_desc(unsigned int irq) } #ifdef CONFIG_SPARSE_IRQ +static const struct kobj_type irq_kobj_type; +#endif + +static int init_desc(struct irq_desc *desc, int irq, int node, + unsigned int flags, + const struct cpumask *affinity, + struct module *owner) +{ + desc->kstat_irqs = alloc_percpu(unsigned int); + if (!desc->kstat_irqs) + return -ENOMEM; + + if (alloc_masks(desc, node)) { + free_percpu(desc->kstat_irqs); + return -ENOMEM; + } + + raw_spin_lock_init(&desc->lock); + lockdep_set_class(&desc->lock, &irq_desc_lock_class); + mutex_init(&desc->request_mutex); + init_waitqueue_head(&desc->wait_for_threads); + desc_set_defaults(irq, desc, node, affinity, owner); + irqd_set(&desc->irq_data, flags); + irq_resend_init(desc); +#ifdef CONFIG_SPARSE_IRQ + kobject_init(&desc->kobj, &irq_kobj_type); + init_rcu_head(&desc->rcu); +#endif + + return 0; +} + +#ifdef CONFIG_SPARSE_IRQ static void irq_kobj_release(struct kobject *kobj); @@ -384,21 +429,6 @@ struct irq_desc *irq_to_desc(unsigned int irq) EXPORT_SYMBOL_GPL(irq_to_desc); #endif -#ifdef CONFIG_SMP -static void free_masks(struct irq_desc *desc) -{ -#ifdef CONFIG_GENERIC_PENDING_IRQ - free_cpumask_var(desc->pending_mask); -#endif - free_cpumask_var(desc->irq_common_data.affinity); -#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK - free_cpumask_var(desc->irq_common_data.effective_affinity); -#endif -} -#else -static inline void free_masks(struct irq_desc *desc) { } -#endif - void irq_lock_sparse(void) { mutex_lock(&sparse_irq_lock); @@ -414,36 +444,19 @@ static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, struct module *owner) { struct irq_desc *desc; + int ret; desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node); if (!desc) return NULL; - /* allocate based on nr_cpu_ids */ - desc->kstat_irqs = alloc_percpu(unsigned int); - if (!desc->kstat_irqs) - goto err_desc; - - if (alloc_masks(desc, node)) - goto err_kstat; - raw_spin_lock_init(&desc->lock); - lockdep_set_class(&desc->lock, &irq_desc_lock_class); - mutex_init(&desc->request_mutex); - init_rcu_head(&desc->rcu); - init_waitqueue_head(&desc->wait_for_threads); - - desc_set_defaults(irq, desc, node, affinity, owner); - irqd_set(&desc->irq_data, flags); - kobject_init(&desc->kobj, &irq_kobj_type); - irq_resend_init(desc); + ret = init_desc(desc, irq, node, flags, affinity, owner); + if (unlikely(ret)) { + kfree(desc); + return NULL; + } return desc; - -err_kstat: - free_percpu(desc->kstat_irqs); -err_desc: - kfree(desc); - return NULL; } static void irq_kobj_release(struct kobject *kobj) @@ -583,26 +596,29 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { int __init early_irq_init(void) { int count, i, node = first_online_node; - struct irq_desc *desc; + int ret; init_irq_default_affinity(); printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS); - desc = irq_desc; count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { - desc[i].kstat_irqs = alloc_percpu(unsigned int); - alloc_masks(&desc[i], node); - raw_spin_lock_init(&desc[i].lock); - lockdep_set_class(&desc[i].lock, &irq_desc_lock_class); - mutex_init(&desc[i].request_mutex); - init_waitqueue_head(&desc[i].wait_for_threads); - desc_set_defaults(i, &desc[i], node, NULL, NULL); - irq_resend_init(&desc[i]); + ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL); + if (unlikely(ret)) + goto __free_desc_res; } + return arch_early_irq_init(); + +__free_desc_res: + while (--i >= 0) { + free_masks(irq_desc + i); + free_percpu(irq_desc[i].kstat_irqs); + } + + return ret; } struct irq_desc *irq_to_desc(unsigned int irq) diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c index 0bdef4fe925b..3dd1c871e091 100644 --- a/kernel/irq/irqdomain.c +++ b/kernel/irq/irqdomain.c @@ -29,6 +29,7 @@ static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base, unsigned int nr_irqs, int node, void *arg, bool realloc, const struct irq_affinity_desc *affinity); static void irq_domain_check_hierarchy(struct irq_domain *domain); +static void irq_domain_free_one_irq(struct irq_domain *domain, unsigned int virq); struct irqchip_fwid { struct fwnode_handle fwnode; @@ -448,7 +449,7 @@ struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec, */ mutex_lock(&irq_domain_mutex); list_for_each_entry(h, &irq_domain_list, link) { - if (h->ops->select && fwspec->param_count) + if (h->ops->select && bus_token != DOMAIN_BUS_ANY) rc = h->ops->select(h, fwspec, bus_token); else if (h->ops->match) rc = h->ops->match(h, to_of_node(fwnode), bus_token); @@ -858,8 +859,13 @@ unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec) } if (irq_domain_is_hierarchy(domain)) { - virq = irq_domain_alloc_irqs_locked(domain, -1, 1, NUMA_NO_NODE, - fwspec, false, NULL); + if (irq_domain_is_msi_device(domain)) { + mutex_unlock(&domain->root->mutex); + virq = msi_device_domain_alloc_wired(domain, hwirq, type); + mutex_lock(&domain->root->mutex); + } else + virq = irq_domain_alloc_irqs_locked(domain, -1, 1, NUMA_NO_NODE, + fwspec, false, NULL); if (virq <= 0) { virq = 0; goto out; @@ -914,7 +920,7 @@ void irq_dispose_mapping(unsigned int virq) return; if (irq_domain_is_hierarchy(domain)) { - irq_domain_free_irqs(virq, 1); + irq_domain_free_one_irq(domain, virq); } else { irq_domain_disassociate(domain, virq); irq_free_desc(virq); @@ -1755,6 +1761,14 @@ void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs) irq_free_descs(virq, nr_irqs); } +static void irq_domain_free_one_irq(struct irq_domain *domain, unsigned int virq) +{ + if (irq_domain_is_msi_device(domain)) + msi_device_domain_free_wired(domain, virq); + else + irq_domain_free_irqs(virq, 1); +} + /** * irq_domain_alloc_irqs_parent - Allocate interrupts from parent domain * @domain: Domain below which interrupts must be allocated @@ -1907,9 +1921,9 @@ static int irq_domain_alloc_irqs_locked(struct irq_domain *domain, int irq_base, return -EINVAL; } -static void irq_domain_check_hierarchy(struct irq_domain *domain) -{ -} +static void irq_domain_check_hierarchy(struct irq_domain *domain) { } +static void irq_domain_free_one_irq(struct irq_domain *domain, unsigned int virq) { } + #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ #ifdef CONFIG_GENERIC_IRQ_DEBUGFS diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 1782f90cd8c6..ad3eaf2ab959 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -192,10 +192,14 @@ void irq_set_thread_affinity(struct irq_desc *desc) struct irqaction *action; for_each_action_of_desc(desc, action) { - if (action->thread) + if (action->thread) { set_bit(IRQTF_AFFINITY, &action->thread_flags); - if (action->secondary && action->secondary->thread) + wake_up_process(action->thread); + } + if (action->secondary && action->secondary->thread) { set_bit(IRQTF_AFFINITY, &action->secondary->thread_flags); + wake_up_process(action->secondary->thread); + } } } @@ -1049,10 +1053,57 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id) return IRQ_NONE; } -static int irq_wait_for_interrupt(struct irqaction *action) +#ifdef CONFIG_SMP +/* + * Check whether we need to change the affinity of the interrupt thread. + */ +static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) +{ + cpumask_var_t mask; + bool valid = false; + + if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags)) + return; + + __set_current_state(TASK_RUNNING); + + /* + * In case we are out of memory we set IRQTF_AFFINITY again and + * try again next time + */ + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { + set_bit(IRQTF_AFFINITY, &action->thread_flags); + return; + } + + raw_spin_lock_irq(&desc->lock); + /* + * This code is triggered unconditionally. Check the affinity + * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out. + */ + if (cpumask_available(desc->irq_common_data.affinity)) { + const struct cpumask *m; + + m = irq_data_get_effective_affinity_mask(&desc->irq_data); + cpumask_copy(mask, m); + valid = true; + } + raw_spin_unlock_irq(&desc->lock); + + if (valid) + set_cpus_allowed_ptr(current, mask); + free_cpumask_var(mask); +} +#else +static inline void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { } +#endif + +static int irq_wait_for_interrupt(struct irq_desc *desc, + struct irqaction *action) { for (;;) { set_current_state(TASK_INTERRUPTIBLE); + irq_thread_check_affinity(desc, action); if (kthread_should_stop()) { /* may need to run one last time */ @@ -1129,52 +1180,6 @@ out_unlock: chip_bus_sync_unlock(desc); } -#ifdef CONFIG_SMP -/* - * Check whether we need to change the affinity of the interrupt thread. - */ -static void -irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) -{ - cpumask_var_t mask; - bool valid = true; - - if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags)) - return; - - /* - * In case we are out of memory we set IRQTF_AFFINITY again and - * try again next time - */ - if (!alloc_cpumask_var(&mask, GFP_KERNEL)) { - set_bit(IRQTF_AFFINITY, &action->thread_flags); - return; - } - - raw_spin_lock_irq(&desc->lock); - /* - * This code is triggered unconditionally. Check the affinity - * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out. - */ - if (cpumask_available(desc->irq_common_data.affinity)) { - const struct cpumask *m; - - m = irq_data_get_effective_affinity_mask(&desc->irq_data); - cpumask_copy(mask, m); - } else { - valid = false; - } - raw_spin_unlock_irq(&desc->lock); - - if (valid) - set_cpus_allowed_ptr(current, mask); - free_cpumask_var(mask); -} -#else -static inline void -irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { } -#endif - /* * Interrupts which are not explicitly requested as threaded * interrupts rely on the implicit bh/preempt disable of the hard irq @@ -1312,13 +1317,9 @@ static int irq_thread(void *data) init_task_work(&on_exit_work, irq_thread_dtor); task_work_add(current, &on_exit_work, TWA_NONE); - irq_thread_check_affinity(desc, action); - - while (!irq_wait_for_interrupt(action)) { + while (!irq_wait_for_interrupt(desc, action)) { irqreturn_t action_ret; - irq_thread_check_affinity(desc, action); - action_ret = handler_fn(desc, action); if (action_ret == IRQ_WAKE_THREAD) irq_wake_secondary(desc, action); diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c index 75d0ae490e29..8f222d1cccec 100644 --- a/kernel/irq/matrix.c +++ b/kernel/irq/matrix.c @@ -8,8 +8,6 @@ #include <linux/cpu.h> #include <linux/irq.h> -#define IRQ_MATRIX_SIZE (BITS_TO_LONGS(IRQ_MATRIX_BITS)) - struct cpumap { unsigned int available; unsigned int allocated; @@ -17,8 +15,8 @@ struct cpumap { unsigned int managed_allocated; bool initialized; bool online; - unsigned long alloc_map[IRQ_MATRIX_SIZE]; - unsigned long managed_map[IRQ_MATRIX_SIZE]; + unsigned long *managed_map; + unsigned long alloc_map[]; }; struct irq_matrix { @@ -32,8 +30,8 @@ struct irq_matrix { unsigned int total_allocated; unsigned int online_maps; struct cpumap __percpu *maps; - unsigned long scratch_map[IRQ_MATRIX_SIZE]; - unsigned long system_map[IRQ_MATRIX_SIZE]; + unsigned long *system_map; + unsigned long scratch_map[]; }; #define CREATE_TRACE_POINTS @@ -50,24 +48,32 @@ __init struct irq_matrix *irq_alloc_matrix(unsigned int matrix_bits, unsigned int alloc_start, unsigned int alloc_end) { + unsigned int cpu, matrix_size = BITS_TO_LONGS(matrix_bits); struct irq_matrix *m; - if (matrix_bits > IRQ_MATRIX_BITS) - return NULL; - - m = kzalloc(sizeof(*m), GFP_KERNEL); + m = kzalloc(struct_size(m, scratch_map, matrix_size * 2), GFP_KERNEL); if (!m) return NULL; + m->system_map = &m->scratch_map[matrix_size]; + m->matrix_bits = matrix_bits; m->alloc_start = alloc_start; m->alloc_end = alloc_end; m->alloc_size = alloc_end - alloc_start; - m->maps = alloc_percpu(*m->maps); + m->maps = __alloc_percpu(struct_size(m->maps, alloc_map, matrix_size * 2), + __alignof__(*m->maps)); if (!m->maps) { kfree(m); return NULL; } + + for_each_possible_cpu(cpu) { + struct cpumap *cm = per_cpu_ptr(m->maps, cpu); + + cm->managed_map = &cm->alloc_map[matrix_size]; + } + return m; } diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c index 79b4a58ba9c3..f90952ebc494 100644 --- a/kernel/irq/msi.c +++ b/kernel/irq/msi.c @@ -726,11 +726,26 @@ static void msi_domain_free(struct irq_domain *domain, unsigned int virq, irq_domain_free_irqs_top(domain, virq, nr_irqs); } +static int msi_domain_translate(struct irq_domain *domain, struct irq_fwspec *fwspec, + irq_hw_number_t *hwirq, unsigned int *type) +{ + struct msi_domain_info *info = domain->host_data; + + /* + * This will catch allocations through the regular irqdomain path except + * for MSI domains which really support this, e.g. MBIGEN. + */ + if (!info->ops->msi_translate) + return -ENOTSUPP; + return info->ops->msi_translate(domain, fwspec, hwirq, type); +} + static const struct irq_domain_ops msi_domain_ops = { .alloc = msi_domain_alloc, .free = msi_domain_free, .activate = msi_domain_activate, .deactivate = msi_domain_deactivate, + .translate = msi_domain_translate, }; static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info, @@ -830,8 +845,11 @@ static struct irq_domain *__msi_create_irq_domain(struct fwnode_handle *fwnode, domain = irq_domain_create_hierarchy(parent, flags | IRQ_DOMAIN_FLAG_MSI, 0, fwnode, &msi_domain_ops, info); - if (domain) + if (domain) { irq_domain_update_bus_token(domain, info->bus_token); + if (info->flags & MSI_FLAG_PARENT_PM_DEV) + domain->pm_dev = parent->pm_dev; + } return domain; } @@ -945,9 +963,9 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, void *chip_data) { struct irq_domain *domain, *parent = dev->msi.domain; - const struct msi_parent_ops *pops; + struct fwnode_handle *fwnode, *fwnalloced = NULL; struct msi_domain_template *bundle; - struct fwnode_handle *fwnode; + const struct msi_parent_ops *pops; if (!irq_domain_is_msi_parent(parent)) return false; @@ -970,7 +988,19 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, pops->prefix ? : "", bundle->chip.name, dev_name(dev)); bundle->chip.name = bundle->name; - fwnode = irq_domain_alloc_named_fwnode(bundle->name); + /* + * Using the device firmware node is required for wire to MSI + * device domains so that the existing firmware results in a domain + * match. + * All other device domains like PCI/MSI use the named firmware + * node as they are not guaranteed to have a fwnode. They are never + * looked up and always handled in the context of the device. + */ + if (bundle->info.flags & MSI_FLAG_USE_DEV_FWNODE) + fwnode = dev->fwnode; + else + fwnode = fwnalloced = irq_domain_alloc_named_fwnode(bundle->name); + if (!fwnode) goto free_bundle; @@ -997,7 +1027,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid, fail: msi_unlock_descs(dev); free_fwnode: - irq_domain_free_fwnode(fwnode); + irq_domain_free_fwnode(fwnalloced); free_bundle: kfree(bundle); return false; @@ -1431,34 +1461,10 @@ int msi_domain_alloc_irqs_all_locked(struct device *dev, unsigned int domid, int return msi_domain_alloc_locked(dev, &ctrl); } -/** - * msi_domain_alloc_irq_at - Allocate an interrupt from a MSI interrupt domain at - * a given index - or at the next free index - * - * @dev: Pointer to device struct of the device for which the interrupts - * are allocated - * @domid: Id of the interrupt domain to operate on - * @index: Index for allocation. If @index == %MSI_ANY_INDEX the allocation - * uses the next free index. - * @affdesc: Optional pointer to an interrupt affinity descriptor structure - * @icookie: Optional pointer to a domain specific per instance cookie. If - * non-NULL the content of the cookie is stored in msi_desc::data. - * Must be NULL for MSI-X allocations - * - * This requires a MSI interrupt domain which lets the core code manage the - * MSI descriptors. - * - * Return: struct msi_map - * - * On success msi_map::index contains the allocated index number and - * msi_map::virq the corresponding Linux interrupt number - * - * On failure msi_map::index contains the error code and msi_map::virq - * is %0. - */ -struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, unsigned int index, - const struct irq_affinity_desc *affdesc, - union msi_instance_cookie *icookie) +static struct msi_map __msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, + unsigned int index, + const struct irq_affinity_desc *affdesc, + union msi_instance_cookie *icookie) { struct msi_ctrl ctrl = { .domid = domid, .nirqs = 1, }; struct irq_domain *domain; @@ -1466,17 +1472,16 @@ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, u struct msi_desc *desc; int ret; - msi_lock_descs(dev); domain = msi_get_device_domain(dev, domid); if (!domain) { map.index = -ENODEV; - goto unlock; + return map; } desc = msi_alloc_desc(dev, 1, affdesc); if (!desc) { map.index = -ENOMEM; - goto unlock; + return map; } if (icookie) @@ -1485,7 +1490,7 @@ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, u ret = msi_insert_desc(dev, desc, domid, index); if (ret) { map.index = ret; - goto unlock; + return map; } ctrl.first = ctrl.last = desc->msi_index; @@ -1498,11 +1503,90 @@ struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, u map.index = desc->msi_index; map.virq = desc->irq; } -unlock: + return map; +} + +/** + * msi_domain_alloc_irq_at - Allocate an interrupt from a MSI interrupt domain at + * a given index - or at the next free index + * + * @dev: Pointer to device struct of the device for which the interrupts + * are allocated + * @domid: Id of the interrupt domain to operate on + * @index: Index for allocation. If @index == %MSI_ANY_INDEX the allocation + * uses the next free index. + * @affdesc: Optional pointer to an interrupt affinity descriptor structure + * @icookie: Optional pointer to a domain specific per instance cookie. If + * non-NULL the content of the cookie is stored in msi_desc::data. + * Must be NULL for MSI-X allocations + * + * This requires a MSI interrupt domain which lets the core code manage the + * MSI descriptors. + * + * Return: struct msi_map + * + * On success msi_map::index contains the allocated index number and + * msi_map::virq the corresponding Linux interrupt number + * + * On failure msi_map::index contains the error code and msi_map::virq + * is %0. + */ +struct msi_map msi_domain_alloc_irq_at(struct device *dev, unsigned int domid, unsigned int index, + const struct irq_affinity_desc *affdesc, + union msi_instance_cookie *icookie) +{ + struct msi_map map; + + msi_lock_descs(dev); + map = __msi_domain_alloc_irq_at(dev, domid, index, affdesc, icookie); msi_unlock_descs(dev); return map; } +/** + * msi_device_domain_alloc_wired - Allocate a "wired" interrupt on @domain + * @domain: The domain to allocate on + * @hwirq: The hardware interrupt number to allocate for + * @type: The interrupt type + * + * This weirdness supports wire to MSI controllers like MBIGEN. + * + * @hwirq is the hardware interrupt number which is handed in from + * irq_create_fwspec_mapping(). As the wire to MSI domain is sparse, but + * sized in firmware, the hardware interrupt number cannot be used as MSI + * index. For the underlying irq chip the MSI index is irrelevant and + * all it needs is the hardware interrupt number. + * + * To handle this the MSI index is allocated with MSI_ANY_INDEX and the + * hardware interrupt number is stored along with the type information in + * msi_desc::cookie so the underlying interrupt chip and domain code can + * retrieve it. + * + * Return: The Linux interrupt number (> 0) or an error code + */ +int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq, + unsigned int type) +{ + unsigned int domid = MSI_DEFAULT_DOMAIN; + union msi_instance_cookie icookie = { }; + struct device *dev = domain->dev; + struct msi_map map = { }; + + if (WARN_ON_ONCE(!dev || domain->bus_token != DOMAIN_BUS_WIRED_TO_MSI)) + return -EINVAL; + + icookie.value = ((u64)type << 32) | hwirq; + + msi_lock_descs(dev); + if (WARN_ON_ONCE(msi_get_device_domain(dev, domid) != domain)) + map.index = -EINVAL; + else + map = __msi_domain_alloc_irq_at(dev, domid, MSI_ANY_INDEX, NULL, &icookie); + msi_unlock_descs(dev); + + return map.index >= 0 ? map.virq : map.index; +} + static void __msi_domain_free_irqs(struct device *dev, struct irq_domain *domain, struct msi_ctrl *ctrl) { @@ -1629,6 +1713,30 @@ void msi_domain_free_irqs_all(struct device *dev, unsigned int domid) } /** + * msi_device_domain_free_wired - Free a wired interrupt in @domain + * @domain: The domain to free the interrupt on + * @virq: The Linux interrupt number to free + * + * This is the counterpart of msi_device_domain_alloc_wired() for the + * weird wired to MSI converting domains. + */ +void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq) +{ + struct msi_desc *desc = irq_get_msi_desc(virq); + struct device *dev = domain->dev; + + if (WARN_ON_ONCE(!dev || !desc || domain->bus_token != DOMAIN_BUS_WIRED_TO_MSI)) + return; + + msi_lock_descs(dev); + if (!WARN_ON_ONCE(msi_get_device_domain(dev, MSI_DEFAULT_DOMAIN) != domain)) { + msi_domain_free_irqs_range_locked(dev, MSI_DEFAULT_DOMAIN, desc->msi_index, + desc->msi_index); + } + msi_unlock_descs(dev); +} + +/** * msi_get_domain_info - Get the MSI interrupt domain info for @domain * @domain: The interrupt domain to retrieve data from * diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c index b4cac76ea5e9..8a689b4ff4f9 100644 --- a/kernel/kallsyms_selftest.c +++ b/kernel/kallsyms_selftest.c @@ -89,7 +89,6 @@ static struct test_item test_items[] = { ITEM_DATA(kallsyms_test_var_data_static), ITEM_DATA(kallsyms_test_var_bss), ITEM_DATA(kallsyms_test_var_data), - ITEM_DATA(vmap_area_list), #endif }; diff --git a/kernel/kexec.c b/kernel/kexec.c index 8f35a5a42af8..bab542fc1463 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -28,12 +28,14 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, struct kimage *image; bool kexec_on_panic = flags & KEXEC_ON_CRASH; +#ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Verify we have a valid entry point */ if ((entry < phys_to_boot_phys(crashk_res.start)) || (entry > phys_to_boot_phys(crashk_res.end))) return -EADDRNOTAVAIL; } +#endif /* Allocate and initialize a controlling structure */ image = do_kimage_alloc_init(); @@ -44,11 +46,13 @@ static int kimage_alloc_init(struct kimage **rimage, unsigned long entry, image->nr_segments = nr_segments; memcpy(image->segment, segments, nr_segments * sizeof(*segments)); +#ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Enable special crash kernel control page alloc policy. */ image->control_page = crashk_res.start; image->type = KEXEC_TYPE_CRASH; } +#endif ret = sanity_check_segment_list(image); if (ret) @@ -99,13 +103,14 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, if (!kexec_trylock()) return -EBUSY; +#ifdef CONFIG_CRASH_DUMP if (flags & KEXEC_ON_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) arch_kexec_unprotect_crashkres(); - } else { + } else +#endif dest_image = &kexec_image; - } if (nr_segments == 0) { /* Uninstall image */ @@ -162,8 +167,10 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments, image = xchg(dest_image, image); out: +#ifdef CONFIG_CRASH_DUMP if ((flags & KEXEC_ON_CRASH) && kexec_crash_image) arch_kexec_protect_crashkres(); +#endif kimage_free(image); out_unlock: diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c index d08fc7b5db97..0e96f6b24344 100644 --- a/kernel/kexec_core.c +++ b/kernel/kexec_core.c @@ -54,30 +54,6 @@ bool kexec_in_progress = false; bool kexec_file_dbg_print; -int kexec_should_crash(struct task_struct *p) -{ - /* - * If crash_kexec_post_notifiers is enabled, don't run - * crash_kexec() here yet, which must be run after panic - * notifiers in panic(). - */ - if (crash_kexec_post_notifiers) - return 0; - /* - * There are 4 panic() calls in make_task_dead() path, each of which - * corresponds to each of these 4 conditions. - */ - if (in_interrupt() || !p->pid || is_global_init(p) || panic_on_oops) - return 1; - return 0; -} - -int kexec_crash_loaded(void) -{ - return !!kexec_crash_image; -} -EXPORT_SYMBOL_GPL(kexec_crash_loaded); - /* * When kexec transitions to the new kernel there is a one-to-one * mapping between physical and virtual addresses. On processors @@ -209,6 +185,7 @@ int sanity_check_segment_list(struct kimage *image) if (total_pages > nr_pages / 2) return -EINVAL; +#ifdef CONFIG_CRASH_DUMP /* * Verify we have good destination addresses. Normally * the caller is responsible for making certain we don't @@ -231,6 +208,7 @@ int sanity_check_segment_list(struct kimage *image) return -EADDRNOTAVAIL; } } +#endif return 0; } @@ -403,6 +381,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, return pages; } +#ifdef CONFIG_CRASH_DUMP static struct page *kimage_alloc_crash_control_pages(struct kimage *image, unsigned int order) { @@ -468,6 +447,7 @@ static struct page *kimage_alloc_crash_control_pages(struct kimage *image, return pages; } +#endif struct page *kimage_alloc_control_pages(struct kimage *image, @@ -479,48 +459,16 @@ struct page *kimage_alloc_control_pages(struct kimage *image, case KEXEC_TYPE_DEFAULT: pages = kimage_alloc_normal_control_pages(image, order); break; +#ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: pages = kimage_alloc_crash_control_pages(image, order); break; +#endif } return pages; } -int kimage_crash_copy_vmcoreinfo(struct kimage *image) -{ - struct page *vmcoreinfo_page; - void *safecopy; - - if (image->type != KEXEC_TYPE_CRASH) - return 0; - - /* - * For kdump, allocate one vmcoreinfo safe copy from the - * crash memory. as we have arch_kexec_protect_crashkres() - * after kexec syscall, we naturally protect it from write - * (even read) access under kernel direct mapping. But on - * the other hand, we still need to operate it when crash - * happens to generate vmcoreinfo note, hereby we rely on - * vmap for this purpose. - */ - vmcoreinfo_page = kimage_alloc_control_pages(image, 0); - if (!vmcoreinfo_page) { - pr_warn("Could not allocate vmcoreinfo buffer\n"); - return -ENOMEM; - } - safecopy = vmap(&vmcoreinfo_page, 1, VM_MAP, PAGE_KERNEL); - if (!safecopy) { - pr_warn("Could not vmap vmcoreinfo buffer\n"); - return -ENOMEM; - } - - image->vmcoreinfo_data_copy = safecopy; - crash_update_vmcoreinfo_safecopy(safecopy); - - return 0; -} - static int kimage_add_entry(struct kimage *image, kimage_entry_t entry) { if (*image->entry != 0) @@ -603,10 +551,12 @@ void kimage_free(struct kimage *image) if (!image) return; +#ifdef CONFIG_CRASH_DUMP if (image->vmcoreinfo_data_copy) { crash_update_vmcoreinfo_safecopy(NULL); vunmap(image->vmcoreinfo_data_copy); } +#endif kimage_free_extra_pages(image); for_each_kimage_entry(image, ptr, entry) { @@ -800,22 +750,24 @@ static int kimage_load_normal_segment(struct kimage *image, PAGE_SIZE - (maddr & ~PAGE_MASK)); uchunk = min(ubytes, mchunk); - /* For file based kexec, source pages are in kernel memory */ - if (image->file_mode) - memcpy(ptr, kbuf, uchunk); - else - result = copy_from_user(ptr, buf, uchunk); + if (uchunk) { + /* For file based kexec, source pages are in kernel memory */ + if (image->file_mode) + memcpy(ptr, kbuf, uchunk); + else + result = copy_from_user(ptr, buf, uchunk); + ubytes -= uchunk; + if (image->file_mode) + kbuf += uchunk; + else + buf += uchunk; + } kunmap_local(ptr); if (result) { result = -EFAULT; goto out; } - ubytes -= uchunk; maddr += mchunk; - if (image->file_mode) - kbuf += mchunk; - else - buf += mchunk; mbytes -= mchunk; cond_resched(); @@ -824,6 +776,7 @@ out: return result; } +#ifdef CONFIG_CRASH_DUMP static int kimage_load_crash_segment(struct kimage *image, struct kexec_segment *segment) { @@ -866,11 +819,18 @@ static int kimage_load_crash_segment(struct kimage *image, memset(ptr + uchunk, 0, mchunk - uchunk); } - /* For file based kexec, source pages are in kernel memory */ - if (image->file_mode) - memcpy(ptr, kbuf, uchunk); - else - result = copy_from_user(ptr, buf, uchunk); + if (uchunk) { + /* For file based kexec, source pages are in kernel memory */ + if (image->file_mode) + memcpy(ptr, kbuf, uchunk); + else + result = copy_from_user(ptr, buf, uchunk); + ubytes -= uchunk; + if (image->file_mode) + kbuf += uchunk; + else + buf += uchunk; + } kexec_flush_icache_page(page); kunmap_local(ptr); arch_kexec_pre_free_pages(page_address(page), 1); @@ -878,12 +838,7 @@ static int kimage_load_crash_segment(struct kimage *image, result = -EFAULT; goto out; } - ubytes -= uchunk; maddr += mchunk; - if (image->file_mode) - kbuf += mchunk; - else - buf += mchunk; mbytes -= mchunk; cond_resched(); @@ -891,6 +846,7 @@ static int kimage_load_crash_segment(struct kimage *image, out: return result; } +#endif int kimage_load_segment(struct kimage *image, struct kexec_segment *segment) @@ -901,9 +857,11 @@ int kimage_load_segment(struct kimage *image, case KEXEC_TYPE_DEFAULT: result = kimage_load_normal_segment(image, segment); break; +#ifdef CONFIG_CRASH_DUMP case KEXEC_TYPE_CRASH: result = kimage_load_crash_segment(image, segment); break; +#endif } return result; @@ -1028,186 +986,6 @@ bool kexec_load_permitted(int kexec_image_type) } /* - * No panic_cpu check version of crash_kexec(). This function is called - * only when panic_cpu holds the current CPU number; this is the only CPU - * which processes crash_kexec routines. - */ -void __noclone __crash_kexec(struct pt_regs *regs) -{ - /* Take the kexec_lock here to prevent sys_kexec_load - * running on one cpu from replacing the crash kernel - * we are using after a panic on a different cpu. - * - * If the crash kernel was not located in a fixed area - * of memory the xchg(&kexec_crash_image) would be - * sufficient. But since I reuse the memory... - */ - if (kexec_trylock()) { - if (kexec_crash_image) { - struct pt_regs fixed_regs; - - crash_setup_regs(&fixed_regs, regs); - crash_save_vmcoreinfo(); - machine_crash_shutdown(&fixed_regs); - machine_kexec(kexec_crash_image); - } - kexec_unlock(); - } -} -STACK_FRAME_NON_STANDARD(__crash_kexec); - -__bpf_kfunc void crash_kexec(struct pt_regs *regs) -{ - int old_cpu, this_cpu; - - /* - * Only one CPU is allowed to execute the crash_kexec() code as with - * panic(). Otherwise parallel calls of panic() and crash_kexec() - * may stop each other. To exclude them, we use panic_cpu here too. - */ - old_cpu = PANIC_CPU_INVALID; - this_cpu = raw_smp_processor_id(); - - if (atomic_try_cmpxchg(&panic_cpu, &old_cpu, this_cpu)) { - /* This is the 1st CPU which comes here, so go ahead. */ - __crash_kexec(regs); - - /* - * Reset panic_cpu to allow another panic()/crash_kexec() - * call. - */ - atomic_set(&panic_cpu, PANIC_CPU_INVALID); - } -} - -static inline resource_size_t crash_resource_size(const struct resource *res) -{ - return !res->end ? 0 : resource_size(res); -} - -ssize_t crash_get_memory_size(void) -{ - ssize_t size = 0; - - if (!kexec_trylock()) - return -EBUSY; - - size += crash_resource_size(&crashk_res); - size += crash_resource_size(&crashk_low_res); - - kexec_unlock(); - return size; -} - -static int __crash_shrink_memory(struct resource *old_res, - unsigned long new_size) -{ - struct resource *ram_res; - - ram_res = kzalloc(sizeof(*ram_res), GFP_KERNEL); - if (!ram_res) - return -ENOMEM; - - ram_res->start = old_res->start + new_size; - ram_res->end = old_res->end; - ram_res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; - ram_res->name = "System RAM"; - - if (!new_size) { - release_resource(old_res); - old_res->start = 0; - old_res->end = 0; - } else { - crashk_res.end = ram_res->start - 1; - } - - crash_free_reserved_phys_range(ram_res->start, ram_res->end); - insert_resource(&iomem_resource, ram_res); - - return 0; -} - -int crash_shrink_memory(unsigned long new_size) -{ - int ret = 0; - unsigned long old_size, low_size; - - if (!kexec_trylock()) - return -EBUSY; - - if (kexec_crash_image) { - ret = -ENOENT; - goto unlock; - } - - low_size = crash_resource_size(&crashk_low_res); - old_size = crash_resource_size(&crashk_res) + low_size; - new_size = roundup(new_size, KEXEC_CRASH_MEM_ALIGN); - if (new_size >= old_size) { - ret = (new_size == old_size) ? 0 : -EINVAL; - goto unlock; - } - - /* - * (low_size > new_size) implies that low_size is greater than zero. - * This also means that if low_size is zero, the else branch is taken. - * - * If low_size is greater than 0, (low_size > new_size) indicates that - * crashk_low_res also needs to be shrunken. Otherwise, only crashk_res - * needs to be shrunken. - */ - if (low_size > new_size) { - ret = __crash_shrink_memory(&crashk_res, 0); - if (ret) - goto unlock; - - ret = __crash_shrink_memory(&crashk_low_res, new_size); - } else { - ret = __crash_shrink_memory(&crashk_res, new_size - low_size); - } - - /* Swap crashk_res and crashk_low_res if needed */ - if (!crashk_res.end && crashk_low_res.end) { - crashk_res.start = crashk_low_res.start; - crashk_res.end = crashk_low_res.end; - release_resource(&crashk_low_res); - crashk_low_res.start = 0; - crashk_low_res.end = 0; - insert_resource(&iomem_resource, &crashk_res); - } - -unlock: - kexec_unlock(); - return ret; -} - -void crash_save_cpu(struct pt_regs *regs, int cpu) -{ - struct elf_prstatus prstatus; - u32 *buf; - - if ((cpu < 0) || (cpu >= nr_cpu_ids)) - return; - - /* Using ELF notes here is opportunistic. - * I need a well defined structure format - * for the data I pass, and I need tags - * on the data to indicate what information I have - * squirrelled away. ELF notes happen to provide - * all of that, so there is no need to invent something new. - */ - buf = (u32 *)per_cpu_ptr(crash_notes, cpu); - if (!buf) - return; - memset(&prstatus, 0, sizeof(prstatus)); - prstatus.common.pr_pid = current->pid; - elf_core_copy_regs(&prstatus.pr_reg, regs); - buf = append_elf_note(buf, KEXEC_CORE_NOTE_NAME, NT_PRSTATUS, - &prstatus, sizeof(prstatus)); - final_note(buf); -} - -/* * Move into place and start executing a preloaded standalone * executable. If nothing was preloaded return an error. */ diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index bef2f6f2571b..2d1db05fbf04 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -285,11 +285,13 @@ kimage_file_alloc_init(struct kimage **rimage, int kernel_fd, kexec_file_dbg_print = !!(flags & KEXEC_FILE_DEBUG); image->file_mode = 1; +#ifdef CONFIG_CRASH_DUMP if (kexec_on_panic) { /* Enable special crash kernel control page alloc policy. */ image->control_page = crashk_res.start; image->type = KEXEC_TYPE_CRASH; } +#endif ret = kimage_file_prepare_segments(image, kernel_fd, initrd_fd, cmdline_ptr, cmdline_len, flags); @@ -349,13 +351,14 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, if (!kexec_trylock()) return -EBUSY; +#ifdef CONFIG_CRASH_DUMP if (image_type == KEXEC_TYPE_CRASH) { dest_image = &kexec_crash_image; if (kexec_crash_image) arch_kexec_unprotect_crashkres(); - } else { + } else +#endif dest_image = &kexec_image; - } if (flags & KEXEC_FILE_UNLOAD) goto exchange; @@ -419,8 +422,10 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd, exchange: image = xchg(dest_image, image); out: +#ifdef CONFIG_CRASH_DUMP if ((flags & KEXEC_FILE_ON_CRASH) && kexec_crash_image) arch_kexec_protect_crashkres(); +#endif kexec_unlock(); kimage_free(image); @@ -535,8 +540,10 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf, phys_addr_t mstart, mend; struct resource res = { }; +#ifdef CONFIG_CRASH_DUMP if (kbuf->image->type == KEXEC_TYPE_CRASH) return func(&crashk_res, kbuf); +#endif /* * Using MEMBLOCK_NONE will properly skip MEMBLOCK_DRIVER_MANAGED. See @@ -595,12 +602,14 @@ static int kexec_walk_memblock(struct kexec_buf *kbuf, static int kexec_walk_resources(struct kexec_buf *kbuf, int (*func)(struct resource *, void *)) { +#ifdef CONFIG_CRASH_DUMP if (kbuf->image->type == KEXEC_TYPE_CRASH) return walk_iomem_res_desc(crashk_res.desc, IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY, crashk_res.start, crashk_res.end, kbuf, func); - else if (kbuf->top_down) +#endif + if (kbuf->top_down) return walk_system_ram_res_rev(0, ULONG_MAX, kbuf, func); else return walk_system_ram_res(0, ULONG_MAX, kbuf, func); diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h index 74da1409cd14..2595defe8c0d 100644 --- a/kernel/kexec_internal.h +++ b/kernel/kexec_internal.h @@ -4,6 +4,8 @@ #include <linux/kexec.h> +struct kexec_segment; + struct kimage *do_kimage_alloc_init(void); int sanity_check_segment_list(struct kimage *image); void kimage_free_page_list(struct list_head *list); diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c index 1d4bc493b2f4..fe7a517fc4ab 100644 --- a/kernel/ksysfs.c +++ b/kernel/ksysfs.c @@ -120,6 +120,7 @@ static ssize_t kexec_loaded_show(struct kobject *kobj, } KERNEL_ATTR_RO(kexec_loaded); +#ifdef CONFIG_CRASH_DUMP static ssize_t kexec_crash_loaded_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -152,9 +153,10 @@ static ssize_t kexec_crash_size_store(struct kobject *kobj, } KERNEL_ATTR_RW(kexec_crash_size); +#endif /* CONFIG_CRASH_DUMP*/ #endif /* CONFIG_KEXEC_CORE */ -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO static ssize_t vmcoreinfo_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -177,7 +179,7 @@ KERNEL_ATTR_RO(crash_elfcorehdr_size); #endif -#endif /* CONFIG_CRASH_CORE */ +#endif /* CONFIG_VMCORE_INFO */ /* whether file capabilities are enabled */ static ssize_t fscaps_show(struct kobject *kobj, @@ -262,10 +264,12 @@ static struct attribute * kernel_attrs[] = { #endif #ifdef CONFIG_KEXEC_CORE &kexec_loaded_attr.attr, +#ifdef CONFIG_CRASH_DUMP &kexec_crash_loaded_attr.attr, &kexec_crash_size_attr.attr, #endif -#ifdef CONFIG_CRASH_CORE +#endif +#ifdef CONFIG_VMCORE_INFO &vmcoreinfo_attr.attr, #ifdef CONFIG_CRASH_HOTPLUG &crash_elfcorehdr_size_attr.attr, diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c index 185bd1c906b0..6083883c4fe0 100644 --- a/kernel/locking/percpu-rwsem.c +++ b/kernel/locking/percpu-rwsem.c @@ -223,9 +223,10 @@ static bool readers_active_check(struct percpu_rw_semaphore *sem) void __sched percpu_down_write(struct percpu_rw_semaphore *sem) { + bool contended = false; + might_sleep(); rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_); - trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE); /* Notify readers to take the slow path. */ rcu_sync_enter(&sem->rss); @@ -234,8 +235,11 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem) * Try set sem->block; this provides writer-writer exclusion. * Having sem->block set makes new readers block. */ - if (!__percpu_down_write_trylock(sem)) + if (!__percpu_down_write_trylock(sem)) { + trace_contention_begin(sem, LCB_F_PERCPU | LCB_F_WRITE); percpu_rwsem_wait(sem, /* .reader = */ false); + contended = true; + } /* smp_mb() implied by __percpu_down_write_trylock() on success -- D matches A */ @@ -247,7 +251,8 @@ void __sched percpu_down_write(struct percpu_rw_semaphore *sem) /* Wait for all active readers to complete. */ rcuwait_wait_event(&sem->writer, readers_active_check(sem), TASK_UNINTERRUPTIBLE); - trace_contention_end(sem, 0); + if (contended) + trace_contention_end(sem, 0); } EXPORT_SYMBOL_GPL(percpu_down_write); diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 6a0184e9c234..ae2b12f68b90 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -294,8 +294,8 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev) { struct pv_node *pn = (struct pv_node *)node; struct pv_node *pp = (struct pv_node *)prev; + bool __maybe_unused wait_early; int loop; - bool wait_early; for (;;) { for (wait_early = false, loop = SPIN_THRESHOLD; loop; loop--) { diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index 4a10e8c16fd2..88d08eeb8bc0 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -237,12 +237,13 @@ static __always_inline bool rt_mutex_cmpxchg_release(struct rt_mutex_base *lock, */ static __always_inline void mark_rt_mutex_waiters(struct rt_mutex_base *lock) { - unsigned long owner, *p = (unsigned long *) &lock->owner; + unsigned long *p = (unsigned long *) &lock->owner; + unsigned long owner, new; + owner = READ_ONCE(*p); do { - owner = *p; - } while (cmpxchg_relaxed(p, owner, - owner | RT_MUTEX_HAS_WAITERS) != owner); + new = owner | RT_MUTEX_HAS_WAITERS; + } while (!try_cmpxchg_relaxed(p, &owner, new)); /* * The cmpxchg loop above is relaxed to avoid back-to-back ACQUIRE diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c index 2340b6d90ec6..c6d17aee4209 100644 --- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -35,7 +35,7 @@ /* * The least significant 2 bits of the owner value has the following * meanings when set. - * - Bit 0: RWSEM_READER_OWNED - The rwsem is owned by readers + * - Bit 0: RWSEM_READER_OWNED - rwsem may be owned by readers (just a hint) * - Bit 1: RWSEM_NONSPINNABLE - Cannot spin on a reader-owned lock * * When the rwsem is reader-owned and a spinning writer has timed out, @@ -1002,8 +1002,8 @@ rwsem_down_read_slowpath(struct rw_semaphore *sem, long count, unsigned int stat /* * To prevent a constant stream of readers from starving a sleeping - * waiter, don't attempt optimistic lock stealing if the lock is - * currently owned by readers. + * writer, don't attempt optimistic lock stealing if the lock is + * very likely owned by readers. */ if ((atomic_long_read(&sem->owner) & RWSEM_READER_OWNED) && (rcnt > 1) && !(count & RWSEM_WRITER_LOCKED)) diff --git a/kernel/module/internal.h b/kernel/module/internal.h index c8b7b4dcf782..2ebece8a789f 100644 --- a/kernel/module/internal.h +++ b/kernel/module/internal.h @@ -322,9 +322,9 @@ static inline struct module *mod_find(unsigned long addr, struct mod_tree_root * } #endif /* CONFIG_MODULES_TREE_LOOKUP */ -void module_enable_ro(const struct module *mod, bool after_init); -void module_enable_nx(const struct module *mod); -void module_enable_x(const struct module *mod); +int module_enable_rodata_ro(const struct module *mod, bool after_init); +int module_enable_data_nx(const struct module *mod); +int module_enable_text_rox(const struct module *mod); int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod); diff --git a/kernel/module/main.c b/kernel/module/main.c index 36681911c05a..e1e8a7a9d6c1 100644 --- a/kernel/module/main.c +++ b/kernel/module/main.c @@ -2489,6 +2489,11 @@ static void do_free_init(struct work_struct *w) } } +void flush_module_init_free_work(void) +{ + flush_work(&init_free_wq); +} + #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "module." /* Default value for module->async_probe_requested */ @@ -2571,7 +2576,9 @@ static noinline int do_init_module(struct module *mod) /* Switch to core kallsyms now init is done: kallsyms may be walking! */ rcu_assign_pointer(mod->kallsyms, &mod->core_kallsyms); #endif - module_enable_ro(mod, true); + ret = module_enable_rodata_ro(mod, true); + if (ret) + goto fail_mutex_unlock; mod_tree_remove_init(mod); module_arch_freeing_init(mod); for_class_mod_mem_type(type, init) { @@ -2593,8 +2600,8 @@ static noinline int do_init_module(struct module *mod) * Note that module_alloc() on most architectures creates W+X page * mappings which won't be cleaned up until do_free_init() runs. Any * code such as mark_rodata_ro() which depends on those mappings to - * be cleaned up needs to sync with the queued work - ie - * rcu_barrier() + * be cleaned up needs to sync with the queued work by invoking + * flush_module_init_free_work(). */ if (llist_add(&freeinit->node, &init_free_list)) schedule_work(&init_free_wq); @@ -2609,6 +2616,8 @@ static noinline int do_init_module(struct module *mod) return 0; +fail_mutex_unlock: + mutex_unlock(&module_mutex); fail_free_freeinit: kfree(freeinit); fail: @@ -2736,9 +2745,15 @@ static int complete_formation(struct module *mod, struct load_info *info) module_bug_finalize(info->hdr, info->sechdrs, mod); module_cfi_finalize(info->hdr, info->sechdrs, mod); - module_enable_ro(mod, false); - module_enable_nx(mod); - module_enable_x(mod); + err = module_enable_rodata_ro(mod, false); + if (err) + goto out_strict_rwx; + err = module_enable_data_nx(mod); + if (err) + goto out_strict_rwx; + err = module_enable_text_rox(mod); + if (err) + goto out_strict_rwx; /* * Mark state as coming so strong_try_module_get() ignores us, @@ -2749,6 +2764,8 @@ static int complete_formation(struct module *mod, struct load_info *info) return 0; +out_strict_rwx: + module_bug_cleanup(mod); out: mutex_unlock(&module_mutex); return err; diff --git a/kernel/module/strict_rwx.c b/kernel/module/strict_rwx.c index a2b656b4e3d2..c45caa4690e5 100644 --- a/kernel/module/strict_rwx.c +++ b/kernel/module/strict_rwx.c @@ -11,13 +11,16 @@ #include <linux/set_memory.h> #include "internal.h" -static void module_set_memory(const struct module *mod, enum mod_mem_type type, - int (*set_memory)(unsigned long start, int num_pages)) +static int module_set_memory(const struct module *mod, enum mod_mem_type type, + int (*set_memory)(unsigned long start, int num_pages)) { const struct module_memory *mod_mem = &mod->mem[type]; + if (!mod_mem->base) + return 0; + set_vm_flush_reset_perms(mod_mem->base); - set_memory((unsigned long)mod_mem->base, mod_mem->size >> PAGE_SHIFT); + return set_memory((unsigned long)mod_mem->base, mod_mem->size >> PAGE_SHIFT); } /* @@ -26,37 +29,53 @@ static void module_set_memory(const struct module *mod, enum mod_mem_type type, * CONFIG_STRICT_MODULE_RWX because they are needed regardless of whether we * are strict. */ -void module_enable_x(const struct module *mod) +int module_enable_text_rox(const struct module *mod) { - for_class_mod_mem_type(type, text) - module_set_memory(mod, type, set_memory_x); + for_class_mod_mem_type(type, text) { + int ret; + + if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + ret = module_set_memory(mod, type, set_memory_rox); + else + ret = module_set_memory(mod, type, set_memory_x); + if (ret) + return ret; + } + return 0; } -void module_enable_ro(const struct module *mod, bool after_init) +int module_enable_rodata_ro(const struct module *mod, bool after_init) { - if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) - return; -#ifdef CONFIG_STRICT_MODULE_RWX - if (!rodata_enabled) - return; -#endif + int ret; + + if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX) || !rodata_enabled) + return 0; - module_set_memory(mod, MOD_TEXT, set_memory_ro); - module_set_memory(mod, MOD_INIT_TEXT, set_memory_ro); - module_set_memory(mod, MOD_RODATA, set_memory_ro); - module_set_memory(mod, MOD_INIT_RODATA, set_memory_ro); + ret = module_set_memory(mod, MOD_RODATA, set_memory_ro); + if (ret) + return ret; + ret = module_set_memory(mod, MOD_INIT_RODATA, set_memory_ro); + if (ret) + return ret; if (after_init) - module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro); + return module_set_memory(mod, MOD_RO_AFTER_INIT, set_memory_ro); + + return 0; } -void module_enable_nx(const struct module *mod) +int module_enable_data_nx(const struct module *mod) { if (!IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) - return; + return 0; - for_class_mod_mem_type(type, data) - module_set_memory(mod, type, set_memory_nx); + for_class_mod_mem_type(type, data) { + int ret = module_set_memory(mod, type, set_memory_nx); + + if (ret) + return ret; + } + return 0; } int module_enforce_rwx_sections(Elf_Ehdr *hdr, Elf_Shdr *sechdrs, diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 15781acaac1c..6ec3deec68c2 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -573,7 +573,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags) if (proc_ns_file(f.file)) err = validate_ns(&nsset, ns); else - err = validate_nsset(&nsset, f.file->private_data); + err = validate_nsset(&nsset, pidfd_pid(f.file)); if (!err) { commit_nsset(&nsset); perf_event_namespaces(current); diff --git a/kernel/padata.c b/kernel/padata.c index 179fb1518070..e3f639ff1670 100644 --- a/kernel/padata.c +++ b/kernel/padata.c @@ -485,7 +485,8 @@ void __init padata_do_multithreaded(struct padata_mt_job *job) struct padata_work my_work, *pw; struct padata_mt_job_state ps; LIST_HEAD(works); - int nworks; + int nworks, nid; + static atomic_t last_used_nid __initdata; if (job->size == 0) return; @@ -517,7 +518,16 @@ void __init padata_do_multithreaded(struct padata_mt_job *job) ps.chunk_size = roundup(ps.chunk_size, job->align); list_for_each_entry(pw, &works, pw_list) - queue_work(system_unbound_wq, &pw->pw_work); + if (job->numa_aware) { + int old_node = atomic_read(&last_used_nid); + + do { + nid = next_node_in(old_node, node_states[N_CPU]); + } while (!atomic_try_cmpxchg(&last_used_nid, &old_node, nid)); + queue_work_node(nid, system_unbound_wq, &pw->pw_work); + } else { + queue_work(system_unbound_wq, &pw->pw_work); + } /* Use the current thread, which saves starting a workqueue worker. */ padata_work_init(&my_work, padata_mt_helper, &ps, PADATA_WORK_ONSTACK); diff --git a/kernel/panic.c b/kernel/panic.c index 2807639aab51..747c3f3d289a 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -73,6 +73,7 @@ EXPORT_SYMBOL_GPL(panic_timeout); #define PANIC_PRINT_FTRACE_INFO 0x00000010 #define PANIC_PRINT_ALL_PRINTK_MSG 0x00000020 #define PANIC_PRINT_ALL_CPU_BT 0x00000040 +#define PANIC_PRINT_BLOCKED_TASKS 0x00000080 unsigned long panic_print; ATOMIC_NOTIFIER_HEAD(panic_notifier_list); @@ -227,6 +228,9 @@ static void panic_print_sys_info(bool console_flush) if (panic_print & PANIC_PRINT_FTRACE_INFO) ftrace_dump(DUMP_ALL); + + if (panic_print & PANIC_PRINT_BLOCKED_TASKS) + show_state_filter(TASK_UNINTERRUPTIBLE); } void check_panic_on_warn(const char *origin) @@ -446,6 +450,14 @@ void panic(const char *fmt, ...) /* Do not scroll important messages printed above */ suppress_printk = 1; + + /* + * The final messages may not have been printed if in a context that + * defers printing (such as NMI) and irq_work is not available. + * Explicitly flush the kernel log buffer one last time. + */ + console_flush_on_panic(CONSOLE_FLUSH_PENDING); + local_irq_enable(); for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); @@ -666,8 +678,13 @@ void __warn(const char *file, int line, void *caller, unsigned taint, pr_warn("WARNING: CPU: %d PID: %d at %pS\n", raw_smp_processor_id(), current->pid, caller); +#pragma GCC diagnostic push +#ifndef __clang__ +#pragma GCC diagnostic ignored "-Wsuggest-attribute=format" +#endif if (args) vprintk(args->fmt, args->args); +#pragma GCC diagnostic pop print_modules(); diff --git a/kernel/pid.c b/kernel/pid.c index b52b10865454..da76ed1873f7 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -42,6 +42,7 @@ #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/idr.h> +#include <linux/pidfs.h> #include <net/sock.h> #include <uapi/linux/pidfd.h> @@ -61,10 +62,13 @@ struct pid init_struct_pid = { int pid_max = PID_MAX_DEFAULT; -#define RESERVED_PIDS 300 - int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; +/* + * Pseudo filesystems start inode numbering after one. We use Reserved + * PIDs as a natural offset. + */ +static u64 pidfs_ino = RESERVED_PIDS; /* * PID-map pages start out as NULL, they get allocated upon @@ -272,6 +276,8 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; + pid->stashed = NULL; + pid->ino = ++pidfs_ino; for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); @@ -349,6 +355,11 @@ static void __change_pid(struct task_struct *task, enum pid_type type, hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; + if (type == PIDTYPE_PID) { + WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID)); + wake_up_all(&pid->wait_pidfd); + } + for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; @@ -391,8 +402,7 @@ void exchange_tids(struct task_struct *left, struct task_struct *right) void transfer_pid(struct task_struct *old, struct task_struct *new, enum pid_type type) { - if (type == PIDTYPE_PID) - new->thread_pid = old->thread_pid; + WARN_ON_ONCE(type == PIDTYPE_PID); hlist_replace_rcu(&old->pid_links[type], &new->pid_links[type]); } @@ -552,11 +562,6 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) * Return the task associated with @pidfd. The function takes a reference on * the returned task. The caller is responsible for releasing that reference. * - * Currently, the process identified by @pidfd is always a thread-group leader. - * This restriction currently exists for all aspects of pidfds including pidfd - * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling - * (only supports thread group leaders). - * * Return: On success, the task_struct associated with the pidfd. * On error, a negative errno number will be returned. */ @@ -595,7 +600,7 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ -int pidfd_create(struct pid *pid, unsigned int flags) +static int pidfd_create(struct pid *pid, unsigned int flags) { int pidfd; struct file *pidfd_file; @@ -615,11 +620,8 @@ int pidfd_create(struct pid *pid, unsigned int flags) * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for - * the process identified by @pid. Currently, the process identified by - * @pid must be a thread-group leader. This restriction currently exists - * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot - * be used with CLONE_THREAD) and pidfd polling (only supports thread group - * leaders). + * the task identified by @pid. Without PIDFD_THREAD flag the target task + * must be a thread-group leader. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. @@ -629,7 +631,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) int fd; struct pid *p; - if (flags & ~PIDFD_NONBLOCK) + if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) return -EINVAL; if (pid <= 0) @@ -682,7 +684,26 @@ static struct file *__pidfd_fget(struct task_struct *task, int fd) up_read(&task->signal->exec_update_lock); - return file ?: ERR_PTR(-EBADF); + if (!file) { + /* + * It is possible that the target thread is exiting; it can be + * either: + * 1. before exit_signals(), which gives a real fd + * 2. before exit_files() takes the task_lock() gives a real fd + * 3. after exit_files() releases task_lock(), ->files is NULL; + * this has PF_EXITING, since it was set in exit_signals(), + * __pidfd_fget() returns EBADF. + * In case 3 we get EBADF, but that really means ESRCH, since + * the task is currently exiting and has freed its files + * struct, so we fix it up. + */ + if (task->flags & PF_EXITING) + file = ERR_PTR(-ESRCH); + else + file = ERR_PTR(-EBADF); + } + + return file; } static int pidfd_getfd(struct pid *pid, int fd) diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index 4b31629c5be4..afce8130d8b9 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -39,9 +39,9 @@ config HIBERNATION bool "Hibernation (aka 'suspend to disk')" depends on SWAP && ARCH_HIBERNATION_POSSIBLE select HIBERNATE_CALLBACKS - select LZO_COMPRESS - select LZO_DECOMPRESS select CRC32 + select CRYPTO + select CRYPTO_LZO help Enable the suspend to disk (STD) functionality, which is usually called "hibernation" in user interfaces. STD checkpoints the @@ -92,6 +92,28 @@ config HIBERNATION_SNAPSHOT_DEV If in doubt, say Y. +choice + prompt "Default compressor" + default HIBERNATION_COMP_LZO + depends on HIBERNATION + +config HIBERNATION_COMP_LZO + bool "lzo" + depends on CRYPTO_LZO + +config HIBERNATION_COMP_LZ4 + bool "lz4" + depends on CRYPTO_LZ4 + +endchoice + +config HIBERNATION_DEF_COMP + string + default "lzo" if HIBERNATION_COMP_LZO + default "lz4" if HIBERNATION_COMP_LZ4 + help + Default compressor to be used for hibernation. + config PM_STD_PARTITION string "Default resume partition" depends on HIBERNATION diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c index 7b44f5b89fa1..b686ac0345bd 100644 --- a/kernel/power/energy_model.c +++ b/kernel/power/energy_model.c @@ -23,6 +23,12 @@ */ static DEFINE_MUTEX(em_pd_mutex); +static void em_cpufreq_update_efficiencies(struct device *dev, + struct em_perf_state *table); +static void em_check_capacity_update(void); +static void em_update_workfn(struct work_struct *work); +static DECLARE_DELAYED_WORK(em_update_work, em_update_workfn); + static bool _is_cpu_device(struct device *dev) { return (dev->bus == &cpu_subsys); @@ -31,19 +37,65 @@ static bool _is_cpu_device(struct device *dev) #ifdef CONFIG_DEBUG_FS static struct dentry *rootdir; -static void em_debug_create_ps(struct em_perf_state *ps, struct dentry *pd) +struct em_dbg_info { + struct em_perf_domain *pd; + int ps_id; +}; + +#define DEFINE_EM_DBG_SHOW(name, fname) \ +static int em_debug_##fname##_show(struct seq_file *s, void *unused) \ +{ \ + struct em_dbg_info *em_dbg = s->private; \ + struct em_perf_state *table; \ + unsigned long val; \ + \ + rcu_read_lock(); \ + table = em_perf_state_from_pd(em_dbg->pd); \ + val = table[em_dbg->ps_id].name; \ + rcu_read_unlock(); \ + \ + seq_printf(s, "%lu\n", val); \ + return 0; \ +} \ +DEFINE_SHOW_ATTRIBUTE(em_debug_##fname) + +DEFINE_EM_DBG_SHOW(frequency, frequency); +DEFINE_EM_DBG_SHOW(power, power); +DEFINE_EM_DBG_SHOW(cost, cost); +DEFINE_EM_DBG_SHOW(performance, performance); +DEFINE_EM_DBG_SHOW(flags, inefficiency); + +static void em_debug_create_ps(struct em_perf_domain *em_pd, + struct em_dbg_info *em_dbg, int i, + struct dentry *pd) { + struct em_perf_state *table; + unsigned long freq; struct dentry *d; char name[24]; - snprintf(name, sizeof(name), "ps:%lu", ps->frequency); + em_dbg[i].pd = em_pd; + em_dbg[i].ps_id = i; + + rcu_read_lock(); + table = em_perf_state_from_pd(em_pd); + freq = table[i].frequency; + rcu_read_unlock(); + + snprintf(name, sizeof(name), "ps:%lu", freq); /* Create per-ps directory */ d = debugfs_create_dir(name, pd); - debugfs_create_ulong("frequency", 0444, d, &ps->frequency); - debugfs_create_ulong("power", 0444, d, &ps->power); - debugfs_create_ulong("cost", 0444, d, &ps->cost); - debugfs_create_ulong("inefficient", 0444, d, &ps->flags); + debugfs_create_file("frequency", 0444, d, &em_dbg[i], + &em_debug_frequency_fops); + debugfs_create_file("power", 0444, d, &em_dbg[i], + &em_debug_power_fops); + debugfs_create_file("cost", 0444, d, &em_dbg[i], + &em_debug_cost_fops); + debugfs_create_file("performance", 0444, d, &em_dbg[i], + &em_debug_performance_fops); + debugfs_create_file("inefficient", 0444, d, &em_dbg[i], + &em_debug_inefficiency_fops); } static int em_debug_cpus_show(struct seq_file *s, void *unused) @@ -66,6 +118,7 @@ DEFINE_SHOW_ATTRIBUTE(em_debug_flags); static void em_debug_create_pd(struct device *dev) { + struct em_dbg_info *em_dbg; struct dentry *d; int i; @@ -79,9 +132,14 @@ static void em_debug_create_pd(struct device *dev) debugfs_create_file("flags", 0444, d, dev->em_pd, &em_debug_flags_fops); + em_dbg = devm_kcalloc(dev, dev->em_pd->nr_perf_states, + sizeof(*em_dbg), GFP_KERNEL); + if (!em_dbg) + return; + /* Create a sub-directory for each performance state */ for (i = 0; i < dev->em_pd->nr_perf_states; i++) - em_debug_create_ps(&dev->em_pd->table[i], d); + em_debug_create_ps(dev->em_pd, em_dbg, i, d); } @@ -103,18 +161,192 @@ static void em_debug_create_pd(struct device *dev) {} static void em_debug_remove_pd(struct device *dev) {} #endif +static void em_destroy_table_rcu(struct rcu_head *rp) +{ + struct em_perf_table __rcu *table; + + table = container_of(rp, struct em_perf_table, rcu); + kfree(table); +} + +static void em_release_table_kref(struct kref *kref) +{ + struct em_perf_table __rcu *table; + + /* It was the last owner of this table so we can free */ + table = container_of(kref, struct em_perf_table, kref); + + call_rcu(&table->rcu, em_destroy_table_rcu); +} + +/** + * em_table_free() - Handles safe free of the EM table when needed + * @table : EM table which is going to be freed + * + * No return values. + */ +void em_table_free(struct em_perf_table __rcu *table) +{ + kref_put(&table->kref, em_release_table_kref); +} + +/** + * em_table_alloc() - Allocate a new EM table + * @pd : EM performance domain for which this must be done + * + * Allocate a new EM table and initialize its kref to indicate that it + * has a user. + * Returns allocated table or NULL. + */ +struct em_perf_table __rcu *em_table_alloc(struct em_perf_domain *pd) +{ + struct em_perf_table __rcu *table; + int table_size; + + table_size = sizeof(struct em_perf_state) * pd->nr_perf_states; + + table = kzalloc(sizeof(*table) + table_size, GFP_KERNEL); + if (!table) + return NULL; + + kref_init(&table->kref); + + return table; +} + +static void em_init_performance(struct device *dev, struct em_perf_domain *pd, + struct em_perf_state *table, int nr_states) +{ + u64 fmax, max_cap; + int i, cpu; + + /* This is needed only for CPUs and EAS skip other devices */ + if (!_is_cpu_device(dev)) + return; + + cpu = cpumask_first(em_span_cpus(pd)); + + /* + * Calculate the performance value for each frequency with + * linear relationship. The final CPU capacity might not be ready at + * boot time, but the EM will be updated a bit later with correct one. + */ + fmax = (u64) table[nr_states - 1].frequency; + max_cap = (u64) arch_scale_cpu_capacity(cpu); + for (i = 0; i < nr_states; i++) + table[i].performance = div64_u64(max_cap * table[i].frequency, + fmax); +} + +static int em_compute_costs(struct device *dev, struct em_perf_state *table, + struct em_data_callback *cb, int nr_states, + unsigned long flags) +{ + unsigned long prev_cost = ULONG_MAX; + int i, ret; + + /* Compute the cost of each performance state. */ + for (i = nr_states - 1; i >= 0; i--) { + unsigned long power_res, cost; + + if ((flags & EM_PERF_DOMAIN_ARTIFICIAL) && cb->get_cost) { + ret = cb->get_cost(dev, table[i].frequency, &cost); + if (ret || !cost || cost > EM_MAX_POWER) { + dev_err(dev, "EM: invalid cost %lu %d\n", + cost, ret); + return -EINVAL; + } + } else { + /* increase resolution of 'cost' precision */ + power_res = table[i].power * 10; + cost = power_res / table[i].performance; + } + + table[i].cost = cost; + + if (table[i].cost >= prev_cost) { + table[i].flags = EM_PERF_STATE_INEFFICIENT; + dev_dbg(dev, "EM: OPP:%lu is inefficient\n", + table[i].frequency); + } else { + prev_cost = table[i].cost; + } + } + + return 0; +} + +/** + * em_dev_compute_costs() - Calculate cost values for new runtime EM table + * @dev : Device for which the EM table is to be updated + * @table : The new EM table that is going to get the costs calculated + * @nr_states : Number of performance states + * + * Calculate the em_perf_state::cost values for new runtime EM table. The + * values are used for EAS during task placement. It also calculates and sets + * the efficiency flag for each performance state. When the function finish + * successfully the EM table is ready to be updated and used by EAS. + * + * Return 0 on success or a proper error in case of failure. + */ +int em_dev_compute_costs(struct device *dev, struct em_perf_state *table, + int nr_states) +{ + return em_compute_costs(dev, table, NULL, nr_states, 0); +} + +/** + * em_dev_update_perf_domain() - Update runtime EM table for a device + * @dev : Device for which the EM is to be updated + * @new_table : The new EM table that is going to be used from now + * + * Update EM runtime modifiable table for the @dev using the provided @table. + * + * This function uses a mutex to serialize writers, so it must not be called + * from a non-sleeping context. + * + * Return 0 on success or an error code on failure. + */ +int em_dev_update_perf_domain(struct device *dev, + struct em_perf_table __rcu *new_table) +{ + struct em_perf_table __rcu *old_table; + struct em_perf_domain *pd; + + if (!dev) + return -EINVAL; + + /* Serialize update/unregister or concurrent updates */ + mutex_lock(&em_pd_mutex); + + if (!dev->em_pd) { + mutex_unlock(&em_pd_mutex); + return -EINVAL; + } + pd = dev->em_pd; + + kref_get(&new_table->kref); + + old_table = pd->em_table; + rcu_assign_pointer(pd->em_table, new_table); + + em_cpufreq_update_efficiencies(dev, new_table->state); + + em_table_free(old_table); + + mutex_unlock(&em_pd_mutex); + return 0; +} +EXPORT_SYMBOL_GPL(em_dev_update_perf_domain); + static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, - int nr_states, struct em_data_callback *cb, + struct em_perf_state *table, + struct em_data_callback *cb, unsigned long flags) { - unsigned long power, freq, prev_freq = 0, prev_cost = ULONG_MAX; - struct em_perf_state *table; + unsigned long power, freq, prev_freq = 0; + int nr_states = pd->nr_perf_states; int i, ret; - u64 fmax; - - table = kcalloc(nr_states, sizeof(*table), GFP_KERNEL); - if (!table) - return -ENOMEM; /* Build the list of performance states for this performance domain */ for (i = 0, freq = 0; i < nr_states; i++, freq++) { @@ -127,7 +359,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, if (ret) { dev_err(dev, "EM: invalid perf. state: %d\n", ret); - goto free_ps_table; + return -EINVAL; } /* @@ -137,7 +369,7 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, if (freq <= prev_freq) { dev_err(dev, "EM: non-increasing freq: %lu\n", freq); - goto free_ps_table; + return -EINVAL; } /* @@ -147,55 +379,27 @@ static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd, if (!power || power > EM_MAX_POWER) { dev_err(dev, "EM: invalid power: %lu\n", power); - goto free_ps_table; + return -EINVAL; } table[i].power = power; table[i].frequency = prev_freq = freq; } - /* Compute the cost of each performance state. */ - fmax = (u64) table[nr_states - 1].frequency; - for (i = nr_states - 1; i >= 0; i--) { - unsigned long power_res, cost; - - if (flags & EM_PERF_DOMAIN_ARTIFICIAL) { - ret = cb->get_cost(dev, table[i].frequency, &cost); - if (ret || !cost || cost > EM_MAX_POWER) { - dev_err(dev, "EM: invalid cost %lu %d\n", - cost, ret); - goto free_ps_table; - } - } else { - power_res = table[i].power; - cost = div64_u64(fmax * power_res, table[i].frequency); - } - - table[i].cost = cost; - - if (table[i].cost >= prev_cost) { - table[i].flags = EM_PERF_STATE_INEFFICIENT; - dev_dbg(dev, "EM: OPP:%lu is inefficient\n", - table[i].frequency); - } else { - prev_cost = table[i].cost; - } - } + em_init_performance(dev, pd, table, nr_states); - pd->table = table; - pd->nr_perf_states = nr_states; + ret = em_compute_costs(dev, table, cb, nr_states, flags); + if (ret) + return -EINVAL; return 0; - -free_ps_table: - kfree(table); - return -EINVAL; } static int em_create_pd(struct device *dev, int nr_states, struct em_data_callback *cb, cpumask_t *cpus, unsigned long flags) { + struct em_perf_table __rcu *em_table; struct em_perf_domain *pd; struct device *cpu_dev; int cpu, ret, num_cpus; @@ -220,11 +424,17 @@ static int em_create_pd(struct device *dev, int nr_states, return -ENOMEM; } - ret = em_create_perf_table(dev, pd, nr_states, cb, flags); - if (ret) { - kfree(pd); - return ret; - } + pd->nr_perf_states = nr_states; + + em_table = em_table_alloc(pd); + if (!em_table) + goto free_pd; + + ret = em_create_perf_table(dev, pd, em_table->state, cb, flags); + if (ret) + goto free_pd_table; + + rcu_assign_pointer(pd->em_table, em_table); if (_is_cpu_device(dev)) for_each_cpu(cpu, cpus) { @@ -235,26 +445,37 @@ static int em_create_pd(struct device *dev, int nr_states, dev->em_pd = pd; return 0; + +free_pd_table: + kfree(em_table); +free_pd: + kfree(pd); + return -EINVAL; } -static void em_cpufreq_update_efficiencies(struct device *dev) +static void +em_cpufreq_update_efficiencies(struct device *dev, struct em_perf_state *table) { struct em_perf_domain *pd = dev->em_pd; - struct em_perf_state *table; struct cpufreq_policy *policy; int found = 0; - int i; + int i, cpu; - if (!_is_cpu_device(dev) || !pd) + if (!_is_cpu_device(dev)) return; - policy = cpufreq_cpu_get(cpumask_first(em_span_cpus(pd))); - if (!policy) { - dev_warn(dev, "EM: Access to CPUFreq policy failed"); + /* Try to get a CPU which is active and in this PD */ + cpu = cpumask_first_and(em_span_cpus(pd), cpu_active_mask); + if (cpu >= nr_cpu_ids) { + dev_warn(dev, "EM: No online CPU for CPUFreq policy\n"); return; } - table = pd->table; + policy = cpufreq_cpu_get(cpu); + if (!policy) { + dev_warn(dev, "EM: Access to CPUFreq policy failed\n"); + return; + } for (i = 0; i < pd->nr_perf_states; i++) { if (!(table[i].flags & EM_PERF_STATE_INEFFICIENT)) @@ -397,13 +618,17 @@ int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states, dev->em_pd->flags |= flags; - em_cpufreq_update_efficiencies(dev); + em_cpufreq_update_efficiencies(dev, dev->em_pd->em_table->state); em_debug_create_pd(dev); dev_info(dev, "EM: created perf domain\n"); unlock: mutex_unlock(&em_pd_mutex); + + if (_is_cpu_device(dev)) + em_check_capacity_update(); + return ret; } EXPORT_SYMBOL_GPL(em_dev_register_perf_domain); @@ -430,9 +655,125 @@ void em_dev_unregister_perf_domain(struct device *dev) mutex_lock(&em_pd_mutex); em_debug_remove_pd(dev); - kfree(dev->em_pd->table); + em_table_free(dev->em_pd->em_table); + kfree(dev->em_pd); dev->em_pd = NULL; mutex_unlock(&em_pd_mutex); } EXPORT_SYMBOL_GPL(em_dev_unregister_perf_domain); + +/* + * Adjustment of CPU performance values after boot, when all CPUs capacites + * are correctly calculated. + */ +static void em_adjust_new_capacity(struct device *dev, + struct em_perf_domain *pd, + u64 max_cap) +{ + struct em_perf_table __rcu *em_table; + struct em_perf_state *ps, *new_ps; + int ret, ps_size; + + em_table = em_table_alloc(pd); + if (!em_table) { + dev_warn(dev, "EM: allocation failed\n"); + return; + } + + new_ps = em_table->state; + + rcu_read_lock(); + ps = em_perf_state_from_pd(pd); + /* Initialize data based on old table */ + ps_size = sizeof(struct em_perf_state) * pd->nr_perf_states; + memcpy(new_ps, ps, ps_size); + + rcu_read_unlock(); + + em_init_performance(dev, pd, new_ps, pd->nr_perf_states); + ret = em_compute_costs(dev, new_ps, NULL, pd->nr_perf_states, + pd->flags); + if (ret) { + dev_warn(dev, "EM: compute costs failed\n"); + return; + } + + ret = em_dev_update_perf_domain(dev, em_table); + if (ret) + dev_warn(dev, "EM: update failed %d\n", ret); + + /* + * This is one-time-update, so give up the ownership in this updater. + * The EM framework has incremented the usage counter and from now + * will keep the reference (then free the memory when needed). + */ + em_table_free(em_table); +} + +static void em_check_capacity_update(void) +{ + cpumask_var_t cpu_done_mask; + struct em_perf_state *table; + struct em_perf_domain *pd; + unsigned long cpu_capacity; + int cpu; + + if (!zalloc_cpumask_var(&cpu_done_mask, GFP_KERNEL)) { + pr_warn("no free memory\n"); + return; + } + + /* Check if CPUs capacity has changed than update EM */ + for_each_possible_cpu(cpu) { + struct cpufreq_policy *policy; + unsigned long em_max_perf; + struct device *dev; + + if (cpumask_test_cpu(cpu, cpu_done_mask)) + continue; + + policy = cpufreq_cpu_get(cpu); + if (!policy) { + pr_debug("Accessing cpu%d policy failed\n", cpu); + schedule_delayed_work(&em_update_work, + msecs_to_jiffies(1000)); + break; + } + cpufreq_cpu_put(policy); + + pd = em_cpu_get(cpu); + if (!pd || em_is_artificial(pd)) + continue; + + cpumask_or(cpu_done_mask, cpu_done_mask, + em_span_cpus(pd)); + + cpu_capacity = arch_scale_cpu_capacity(cpu); + + rcu_read_lock(); + table = em_perf_state_from_pd(pd); + em_max_perf = table[pd->nr_perf_states - 1].performance; + rcu_read_unlock(); + + /* + * Check if the CPU capacity has been adjusted during boot + * and trigger the update for new performance values. + */ + if (em_max_perf == cpu_capacity) + continue; + + pr_debug("updating cpu%d cpu_cap=%lu old capacity=%lu\n", + cpu, cpu_capacity, em_max_perf); + + dev = get_cpu_device(cpu); + em_adjust_new_capacity(dev, pd, cpu_capacity); + } + + free_cpumask_var(cpu_done_mask); +} + +static void em_update_workfn(struct work_struct *work) +{ + em_check_capacity_update(); +} diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 4b0b7cf2e019..43b1a82e800c 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -47,6 +47,15 @@ dev_t swsusp_resume_device; sector_t swsusp_resume_block; __visible int in_suspend __nosavedata; +static char hibernate_compressor[CRYPTO_MAX_ALG_NAME] = CONFIG_HIBERNATION_DEF_COMP; + +/* + * Compression/decompression algorithm to be used while saving/loading + * image to/from disk. This would later be used in 'kernel/power/swap.c' + * to allocate comp streams. + */ +char hib_comp_algo[CRYPTO_MAX_ALG_NAME]; + enum { HIBERNATION_INVALID, HIBERNATION_PLATFORM, @@ -718,6 +727,9 @@ static int load_image_and_restore(void) return error; } +#define COMPRESSION_ALGO_LZO "lzo" +#define COMPRESSION_ALGO_LZ4 "lz4" + /** * hibernate - Carry out system hibernation, including saving the image. */ @@ -732,6 +744,17 @@ int hibernate(void) return -EPERM; } + /* + * Query for the compression algorithm support if compression is enabled. + */ + if (!nocompress) { + strscpy(hib_comp_algo, hibernate_compressor, sizeof(hib_comp_algo)); + if (crypto_has_comp(hib_comp_algo, 0, 0) != 1) { + pr_err("%s compression is not available\n", hib_comp_algo); + return -EOPNOTSUPP; + } + } + sleep_flags = lock_system_sleep(); /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { @@ -766,11 +789,24 @@ int hibernate(void) if (hibernation_mode == HIBERNATION_PLATFORM) flags |= SF_PLATFORM_MODE; - if (nocompress) + if (nocompress) { flags |= SF_NOCOMPRESS_MODE; - else + } else { flags |= SF_CRC32_MODE; + /* + * By default, LZO compression is enabled. Use SF_COMPRESSION_ALG_LZ4 + * to override this behaviour and use LZ4. + * + * Refer kernel/power/power.h for more details + */ + + if (!strcmp(hib_comp_algo, COMPRESSION_ALGO_LZ4)) + flags |= SF_COMPRESSION_ALG_LZ4; + else + flags |= SF_COMPRESSION_ALG_LZO; + } + pm_pr_dbg("Writing hibernation image.\n"); error = swsusp_write(flags); swsusp_free(); @@ -955,6 +991,22 @@ static int software_resume(void) if (error) goto Unlock; + /* + * Check if the hibernation image is compressed. If so, query for + * the algorithm support. + */ + if (!(swsusp_header_flags & SF_NOCOMPRESS_MODE)) { + if (swsusp_header_flags & SF_COMPRESSION_ALG_LZ4) + strscpy(hib_comp_algo, COMPRESSION_ALGO_LZ4, sizeof(hib_comp_algo)); + else + strscpy(hib_comp_algo, COMPRESSION_ALGO_LZO, sizeof(hib_comp_algo)); + if (crypto_has_comp(hib_comp_algo, 0, 0) != 1) { + pr_err("%s compression is not available\n", hib_comp_algo); + error = -EOPNOTSUPP; + goto Unlock; + } + } + /* The snapshot device should not be opened while we're running */ if (!hibernate_acquire()) { error = -EBUSY; @@ -1370,6 +1422,57 @@ static int __init nohibernate_setup(char *str) return 1; } +static const char * const comp_alg_enabled[] = { +#if IS_ENABLED(CONFIG_CRYPTO_LZO) + COMPRESSION_ALGO_LZO, +#endif +#if IS_ENABLED(CONFIG_CRYPTO_LZ4) + COMPRESSION_ALGO_LZ4, +#endif +}; + +static int hibernate_compressor_param_set(const char *compressor, + const struct kernel_param *kp) +{ + unsigned int sleep_flags; + int index, ret; + + sleep_flags = lock_system_sleep(); + + index = sysfs_match_string(comp_alg_enabled, compressor); + if (index >= 0) { + ret = param_set_copystring(comp_alg_enabled[index], kp); + if (!ret) + strscpy(hib_comp_algo, comp_alg_enabled[index], + sizeof(hib_comp_algo)); + } else { + ret = index; + } + + unlock_system_sleep(sleep_flags); + + if (ret) + pr_debug("Cannot set specified compressor %s\n", + compressor); + + return ret; +} + +static const struct kernel_param_ops hibernate_compressor_param_ops = { + .set = hibernate_compressor_param_set, + .get = param_get_string, +}; + +static struct kparam_string hibernate_compressor_param_string = { + .maxlen = sizeof(hibernate_compressor), + .string = hibernate_compressor, +}; + +module_param_cb(compressor, &hibernate_compressor_param_ops, + &hibernate_compressor_param_string, 0644); +MODULE_PARM_DESC(compressor, + "Compression algorithm to be used with hibernation"); + __setup("noresume", noresume_setup); __setup("resume_offset=", resume_offset_setup); __setup("resume=", resume_setup); diff --git a/kernel/power/main.c b/kernel/power/main.c index b1ae9b677d03..a9e0693aaf69 100644 --- a/kernel/power/main.c +++ b/kernel/power/main.c @@ -95,19 +95,6 @@ int unregister_pm_notifier(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(unregister_pm_notifier); -void pm_report_hw_sleep_time(u64 t) -{ - suspend_stats.last_hw_sleep = t; - suspend_stats.total_hw_sleep += t; -} -EXPORT_SYMBOL_GPL(pm_report_hw_sleep_time); - -void pm_report_max_hw_sleep(u64 t) -{ - suspend_stats.max_hw_sleep = t; -} -EXPORT_SYMBOL_GPL(pm_report_max_hw_sleep); - int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down) { int ret; @@ -319,26 +306,86 @@ static ssize_t pm_test_store(struct kobject *kobj, struct kobj_attribute *attr, power_attr(pm_test); #endif /* CONFIG_PM_SLEEP_DEBUG */ -static char *suspend_step_name(enum suspend_stat_step step) -{ - switch (step) { - case SUSPEND_FREEZE: - return "freeze"; - case SUSPEND_PREPARE: - return "prepare"; - case SUSPEND_SUSPEND: - return "suspend"; - case SUSPEND_SUSPEND_NOIRQ: - return "suspend_noirq"; - case SUSPEND_RESUME_NOIRQ: - return "resume_noirq"; - case SUSPEND_RESUME: - return "resume"; - default: - return ""; +#define SUSPEND_NR_STEPS SUSPEND_RESUME +#define REC_FAILED_NUM 2 + +struct suspend_stats { + unsigned int step_failures[SUSPEND_NR_STEPS]; + unsigned int success; + unsigned int fail; + int last_failed_dev; + char failed_devs[REC_FAILED_NUM][40]; + int last_failed_errno; + int errno[REC_FAILED_NUM]; + int last_failed_step; + u64 last_hw_sleep; + u64 total_hw_sleep; + u64 max_hw_sleep; + enum suspend_stat_step failed_steps[REC_FAILED_NUM]; +}; + +static struct suspend_stats suspend_stats; +static DEFINE_MUTEX(suspend_stats_lock); + +void dpm_save_failed_dev(const char *name) +{ + mutex_lock(&suspend_stats_lock); + + strscpy(suspend_stats.failed_devs[suspend_stats.last_failed_dev], + name, sizeof(suspend_stats.failed_devs[0])); + suspend_stats.last_failed_dev++; + suspend_stats.last_failed_dev %= REC_FAILED_NUM; + + mutex_unlock(&suspend_stats_lock); +} + +void dpm_save_failed_step(enum suspend_stat_step step) +{ + suspend_stats.step_failures[step-1]++; + suspend_stats.failed_steps[suspend_stats.last_failed_step] = step; + suspend_stats.last_failed_step++; + suspend_stats.last_failed_step %= REC_FAILED_NUM; +} + +void dpm_save_errno(int err) +{ + if (!err) { + suspend_stats.success++; + return; } + + suspend_stats.fail++; + + suspend_stats.errno[suspend_stats.last_failed_errno] = err; + suspend_stats.last_failed_errno++; + suspend_stats.last_failed_errno %= REC_FAILED_NUM; } +void pm_report_hw_sleep_time(u64 t) +{ + suspend_stats.last_hw_sleep = t; + suspend_stats.total_hw_sleep += t; +} +EXPORT_SYMBOL_GPL(pm_report_hw_sleep_time); + +void pm_report_max_hw_sleep(u64 t) +{ + suspend_stats.max_hw_sleep = t; +} +EXPORT_SYMBOL_GPL(pm_report_max_hw_sleep); + +static const char * const suspend_step_names[] = { + [SUSPEND_WORKING] = "", + [SUSPEND_FREEZE] = "freeze", + [SUSPEND_PREPARE] = "prepare", + [SUSPEND_SUSPEND] = "suspend", + [SUSPEND_SUSPEND_LATE] = "suspend_late", + [SUSPEND_SUSPEND_NOIRQ] = "suspend_noirq", + [SUSPEND_RESUME_NOIRQ] = "resume_noirq", + [SUSPEND_RESUME_EARLY] = "resume_early", + [SUSPEND_RESUME] = "resume", +}; + #define suspend_attr(_name, format_str) \ static ssize_t _name##_show(struct kobject *kobj, \ struct kobj_attribute *attr, char *buf) \ @@ -347,20 +394,30 @@ static ssize_t _name##_show(struct kobject *kobj, \ } \ static struct kobj_attribute _name = __ATTR_RO(_name) -suspend_attr(success, "%d\n"); -suspend_attr(fail, "%d\n"); -suspend_attr(failed_freeze, "%d\n"); -suspend_attr(failed_prepare, "%d\n"); -suspend_attr(failed_suspend, "%d\n"); -suspend_attr(failed_suspend_late, "%d\n"); -suspend_attr(failed_suspend_noirq, "%d\n"); -suspend_attr(failed_resume, "%d\n"); -suspend_attr(failed_resume_early, "%d\n"); -suspend_attr(failed_resume_noirq, "%d\n"); +suspend_attr(success, "%u\n"); +suspend_attr(fail, "%u\n"); suspend_attr(last_hw_sleep, "%llu\n"); suspend_attr(total_hw_sleep, "%llu\n"); suspend_attr(max_hw_sleep, "%llu\n"); +#define suspend_step_attr(_name, step) \ +static ssize_t _name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ +{ \ + return sprintf(buf, "%u\n", \ + suspend_stats.step_failures[step-1]); \ +} \ +static struct kobj_attribute _name = __ATTR_RO(_name) + +suspend_step_attr(failed_freeze, SUSPEND_FREEZE); +suspend_step_attr(failed_prepare, SUSPEND_PREPARE); +suspend_step_attr(failed_suspend, SUSPEND_SUSPEND); +suspend_step_attr(failed_suspend_late, SUSPEND_SUSPEND_LATE); +suspend_step_attr(failed_suspend_noirq, SUSPEND_SUSPEND_NOIRQ); +suspend_step_attr(failed_resume, SUSPEND_RESUME); +suspend_step_attr(failed_resume_early, SUSPEND_RESUME_EARLY); +suspend_step_attr(failed_resume_noirq, SUSPEND_RESUME_NOIRQ); + static ssize_t last_failed_dev_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { @@ -392,16 +449,14 @@ static struct kobj_attribute last_failed_errno = __ATTR_RO(last_failed_errno); static ssize_t last_failed_step_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { - int index; enum suspend_stat_step step; - char *last_failed_step = NULL; + int index; index = suspend_stats.last_failed_step + REC_FAILED_NUM - 1; index %= REC_FAILED_NUM; step = suspend_stats.failed_steps[index]; - last_failed_step = suspend_step_name(step); - return sprintf(buf, "%s\n", last_failed_step); + return sprintf(buf, "%s\n", suspend_step_names[step]); } static struct kobj_attribute last_failed_step = __ATTR_RO(last_failed_step); @@ -449,6 +504,7 @@ static const struct attribute_group suspend_attr_group = { static int suspend_stats_show(struct seq_file *s, void *unused) { int i, index, last_dev, last_errno, last_step; + enum suspend_stat_step step; last_dev = suspend_stats.last_failed_dev + REC_FAILED_NUM - 1; last_dev %= REC_FAILED_NUM; @@ -456,47 +512,35 @@ static int suspend_stats_show(struct seq_file *s, void *unused) last_errno %= REC_FAILED_NUM; last_step = suspend_stats.last_failed_step + REC_FAILED_NUM - 1; last_step %= REC_FAILED_NUM; - seq_printf(s, "%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n" - "%s: %d\n%s: %d\n%s: %d\n%s: %d\n%s: %d\n", - "success", suspend_stats.success, - "fail", suspend_stats.fail, - "failed_freeze", suspend_stats.failed_freeze, - "failed_prepare", suspend_stats.failed_prepare, - "failed_suspend", suspend_stats.failed_suspend, - "failed_suspend_late", - suspend_stats.failed_suspend_late, - "failed_suspend_noirq", - suspend_stats.failed_suspend_noirq, - "failed_resume", suspend_stats.failed_resume, - "failed_resume_early", - suspend_stats.failed_resume_early, - "failed_resume_noirq", - suspend_stats.failed_resume_noirq); + + seq_printf(s, "success: %u\nfail: %u\n", + suspend_stats.success, suspend_stats.fail); + + for (step = SUSPEND_FREEZE; step <= SUSPEND_NR_STEPS; step++) + seq_printf(s, "failed_%s: %u\n", suspend_step_names[step], + suspend_stats.step_failures[step-1]); + seq_printf(s, "failures:\n last_failed_dev:\t%-s\n", - suspend_stats.failed_devs[last_dev]); + suspend_stats.failed_devs[last_dev]); for (i = 1; i < REC_FAILED_NUM; i++) { index = last_dev + REC_FAILED_NUM - i; index %= REC_FAILED_NUM; - seq_printf(s, "\t\t\t%-s\n", - suspend_stats.failed_devs[index]); + seq_printf(s, "\t\t\t%-s\n", suspend_stats.failed_devs[index]); } seq_printf(s, " last_failed_errno:\t%-d\n", suspend_stats.errno[last_errno]); for (i = 1; i < REC_FAILED_NUM; i++) { index = last_errno + REC_FAILED_NUM - i; index %= REC_FAILED_NUM; - seq_printf(s, "\t\t\t%-d\n", - suspend_stats.errno[index]); + seq_printf(s, "\t\t\t%-d\n", suspend_stats.errno[index]); } seq_printf(s, " last_failed_step:\t%-s\n", - suspend_step_name( - suspend_stats.failed_steps[last_step])); + suspend_step_names[suspend_stats.failed_steps[last_step]]); for (i = 1; i < REC_FAILED_NUM; i++) { index = last_step + REC_FAILED_NUM - i; index %= REC_FAILED_NUM; seq_printf(s, "\t\t\t%-s\n", - suspend_step_name( - suspend_stats.failed_steps[index])); + suspend_step_names[suspend_stats.failed_steps[index]]); } return 0; diff --git a/kernel/power/power.h b/kernel/power/power.h index 8499a39c62f4..de0e6b1077f2 100644 --- a/kernel/power/power.h +++ b/kernel/power/power.h @@ -6,6 +6,7 @@ #include <linux/compiler.h> #include <linux/cpu.h> #include <linux/cpuidle.h> +#include <linux/crypto.h> struct swsusp_info { struct new_utsname uts; @@ -54,6 +55,10 @@ asmlinkage int swsusp_save(void); /* kernel/power/hibernate.c */ extern bool freezer_test_done; +extern char hib_comp_algo[CRYPTO_MAX_ALG_NAME]; + +/* kernel/power/swap.c */ +extern unsigned int swsusp_header_flags; extern int hibernation_snapshot(int platform_mode); extern int hibernation_restore(int platform_mode); @@ -148,7 +153,7 @@ extern unsigned int snapshot_additional_pages(struct zone *zone); extern unsigned long snapshot_get_image_size(void); extern int snapshot_read_next(struct snapshot_handle *handle); extern int snapshot_write_next(struct snapshot_handle *handle); -extern void snapshot_write_finalize(struct snapshot_handle *handle); +int snapshot_write_finalize(struct snapshot_handle *handle); extern int snapshot_image_loaded(struct snapshot_handle *handle); extern bool hibernate_acquire(void); @@ -162,11 +167,25 @@ extern int swsusp_swap_in_use(void); * Flags that can be passed from the hibernatig hernel to the "boot" kernel in * the image header. */ +#define SF_COMPRESSION_ALG_LZO 0 /* dummy, details given below */ #define SF_PLATFORM_MODE 1 #define SF_NOCOMPRESS_MODE 2 #define SF_CRC32_MODE 4 #define SF_HW_SIG 8 +/* + * Bit to indicate the compression algorithm to be used(for LZ4). The same + * could be checked while saving/loading image to/from disk to use the + * corresponding algorithms. + * + * By default, LZO compression is enabled if SF_CRC32_MODE is set. Use + * SF_COMPRESSION_ALG_LZ4 to override this behaviour and use LZ4. + * + * SF_CRC32_MODE, SF_COMPRESSION_ALG_LZO(dummy) -> Compression, LZO + * SF_CRC32_MODE, SF_COMPRESSION_ALG_LZ4 -> Compression, LZ4 + */ +#define SF_COMPRESSION_ALG_LZ4 16 + /* kernel/power/hibernate.c */ int swsusp_check(bool exclusive); extern void swsusp_free(void); @@ -327,3 +346,5 @@ static inline void pm_sleep_enable_secondary_cpus(void) suspend_enable_secondary_cpus(); cpuidle_resume(); } + +void dpm_save_errno(int err); diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 5c96ff067c64..405eddbda4fc 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -58,22 +58,24 @@ static inline void hibernate_restore_protection_end(void) hibernate_restore_protection_active = false; } -static inline void hibernate_restore_protect_page(void *page_address) +static inline int __must_check hibernate_restore_protect_page(void *page_address) { if (hibernate_restore_protection_active) - set_memory_ro((unsigned long)page_address, 1); + return set_memory_ro((unsigned long)page_address, 1); + return 0; } -static inline void hibernate_restore_unprotect_page(void *page_address) +static inline int hibernate_restore_unprotect_page(void *page_address) { if (hibernate_restore_protection_active) - set_memory_rw((unsigned long)page_address, 1); + return set_memory_rw((unsigned long)page_address, 1); + return 0; } #else static inline void hibernate_restore_protection_begin(void) {} static inline void hibernate_restore_protection_end(void) {} -static inline void hibernate_restore_protect_page(void *page_address) {} -static inline void hibernate_restore_unprotect_page(void *page_address) {} +static inline int __must_check hibernate_restore_protect_page(void *page_address) {return 0; } +static inline int hibernate_restore_unprotect_page(void *page_address) {return 0; } #endif /* CONFIG_STRICT_KERNEL_RWX && CONFIG_ARCH_HAS_SET_MEMORY */ @@ -2832,7 +2834,9 @@ next: } } else { copy_last_highmem_page(); - hibernate_restore_protect_page(handle->buffer); + error = hibernate_restore_protect_page(handle->buffer); + if (error) + return error; handle->buffer = get_buffer(&orig_bm, &ca); if (IS_ERR(handle->buffer)) return PTR_ERR(handle->buffer); @@ -2858,15 +2862,18 @@ next: * stored in highmem. Additionally, it recycles bitmap memory that's not * necessary any more. */ -void snapshot_write_finalize(struct snapshot_handle *handle) +int snapshot_write_finalize(struct snapshot_handle *handle) { + int error; + copy_last_highmem_page(); - hibernate_restore_protect_page(handle->buffer); + error = hibernate_restore_protect_page(handle->buffer); /* Do that only if we have loaded the image entirely */ if (handle->cur > 1 && handle->cur > nr_meta_pages + nr_copy_pages + nr_zero_pages) { memory_bm_recycle(&orig_bm); free_highmem_data(); } + return error; } int snapshot_image_loaded(struct snapshot_handle *handle) diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index fa3bf161d13f..e3ae93bbcb9b 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -192,6 +192,7 @@ static int __init mem_sleep_default_setup(char *str) if (mem_sleep_labels[state] && !strcmp(str, mem_sleep_labels[state])) { mem_sleep_default = state; + mem_sleep_current = state; break; } @@ -367,7 +368,6 @@ static int suspend_prepare(suspend_state_t state) if (!error) return 0; - suspend_stats.failed_freeze++; dpm_save_failed_step(SUSPEND_FREEZE); pm_notifier_call_chain(PM_POST_SUSPEND); Restore: @@ -617,12 +617,7 @@ int pm_suspend(suspend_state_t state) pr_info("suspend entry (%s)\n", mem_sleep_labels[state]); error = enter_state(state); - if (error) { - suspend_stats.fail++; - dpm_save_failed_errno(error); - } else { - suspend_stats.success++; - } + dpm_save_errno(error); pr_info("suspend exit\n"); return error; } diff --git a/kernel/power/swap.c b/kernel/power/swap.c index 6053ddddaf65..5bc04bfe2db1 100644 --- a/kernel/power/swap.c +++ b/kernel/power/swap.c @@ -23,7 +23,6 @@ #include <linux/swapops.h> #include <linux/pm.h> #include <linux/slab.h> -#include <linux/lzo.h> #include <linux/vmalloc.h> #include <linux/cpumask.h> #include <linux/atomic.h> @@ -222,7 +221,7 @@ int swsusp_swap_in_use(void) */ static unsigned short root_swap = 0xffff; -static struct bdev_handle *hib_resume_bdev_handle; +static struct file *hib_resume_bdev_file; struct hib_bio_batch { atomic_t count; @@ -276,7 +275,7 @@ static int hib_submit_io(blk_opf_t opf, pgoff_t page_off, void *addr, struct bio *bio; int error = 0; - bio = bio_alloc(hib_resume_bdev_handle->bdev, 1, opf, + bio = bio_alloc(file_bdev(hib_resume_bdev_file), 1, opf, GFP_NOIO | __GFP_HIGH); bio->bi_iter.bi_sector = page_off * (PAGE_SIZE >> 9); @@ -339,6 +338,13 @@ static int mark_swapfiles(struct swap_map_handle *handle, unsigned int flags) return error; } +/* + * Hold the swsusp_header flag. This is used in software_resume() in + * 'kernel/power/hibernate' to check if the image is compressed and query + * for the compression algorithm support(if so). + */ +unsigned int swsusp_header_flags; + /** * swsusp_swap_check - check if the resume device is a swap device * and get its index (if so) @@ -357,14 +363,14 @@ static int swsusp_swap_check(void) return res; root_swap = res; - hib_resume_bdev_handle = bdev_open_by_dev(swsusp_resume_device, + hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device, BLK_OPEN_WRITE, NULL, NULL); - if (IS_ERR(hib_resume_bdev_handle)) - return PTR_ERR(hib_resume_bdev_handle); + if (IS_ERR(hib_resume_bdev_file)) + return PTR_ERR(hib_resume_bdev_file); - res = set_blocksize(hib_resume_bdev_handle->bdev, PAGE_SIZE); + res = set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE); if (res < 0) - bdev_release(hib_resume_bdev_handle); + fput(hib_resume_bdev_file); return res; } @@ -514,25 +520,30 @@ static int swap_writer_finish(struct swap_map_handle *handle, return error; } +/* + * Bytes we need for compressed data in worst case. We assume(limitation) + * this is the worst of all the compression algorithms. + */ +#define bytes_worst_compress(x) ((x) + ((x) / 16) + 64 + 3 + 2) + /* We need to remember how much compressed data we need to read. */ -#define LZO_HEADER sizeof(size_t) +#define CMP_HEADER sizeof(size_t) /* Number of pages/bytes we'll compress at one time. */ -#define LZO_UNC_PAGES 32 -#define LZO_UNC_SIZE (LZO_UNC_PAGES * PAGE_SIZE) +#define UNC_PAGES 32 +#define UNC_SIZE (UNC_PAGES * PAGE_SIZE) -/* Number of pages/bytes we need for compressed data (worst case). */ -#define LZO_CMP_PAGES DIV_ROUND_UP(lzo1x_worst_compress(LZO_UNC_SIZE) + \ - LZO_HEADER, PAGE_SIZE) -#define LZO_CMP_SIZE (LZO_CMP_PAGES * PAGE_SIZE) +/* Number of pages we need for compressed data (worst case). */ +#define CMP_PAGES DIV_ROUND_UP(bytes_worst_compress(UNC_SIZE) + \ + CMP_HEADER, PAGE_SIZE) +#define CMP_SIZE (CMP_PAGES * PAGE_SIZE) /* Maximum number of threads for compression/decompression. */ -#define LZO_THREADS 3 +#define CMP_THREADS 3 /* Minimum/maximum number of pages for read buffering. */ -#define LZO_MIN_RD_PAGES 1024 -#define LZO_MAX_RD_PAGES 8192 - +#define CMP_MIN_RD_PAGES 1024 +#define CMP_MAX_RD_PAGES 8192 /** * save_image - save the suspend image data @@ -593,8 +604,8 @@ struct crc_data { wait_queue_head_t go; /* start crc update */ wait_queue_head_t done; /* crc update done */ u32 *crc32; /* points to handle's crc32 */ - size_t *unc_len[LZO_THREADS]; /* uncompressed lengths */ - unsigned char *unc[LZO_THREADS]; /* uncompressed data */ + size_t *unc_len[CMP_THREADS]; /* uncompressed lengths */ + unsigned char *unc[CMP_THREADS]; /* uncompressed data */ }; /* @@ -625,10 +636,11 @@ static int crc32_threadfn(void *data) return 0; } /* - * Structure used for LZO data compression. + * Structure used for data compression. */ struct cmp_data { struct task_struct *thr; /* thread */ + struct crypto_comp *cc; /* crypto compressor stream */ atomic_t ready; /* ready to start flag */ atomic_t stop; /* ready to stop flag */ int ret; /* return code */ @@ -636,17 +648,20 @@ struct cmp_data { wait_queue_head_t done; /* compression done */ size_t unc_len; /* uncompressed length */ size_t cmp_len; /* compressed length */ - unsigned char unc[LZO_UNC_SIZE]; /* uncompressed buffer */ - unsigned char cmp[LZO_CMP_SIZE]; /* compressed buffer */ - unsigned char wrk[LZO1X_1_MEM_COMPRESS]; /* compression workspace */ + unsigned char unc[UNC_SIZE]; /* uncompressed buffer */ + unsigned char cmp[CMP_SIZE]; /* compressed buffer */ }; +/* Indicates the image size after compression */ +static atomic_t compressed_size = ATOMIC_INIT(0); + /* * Compression function that runs in its own thread. */ -static int lzo_compress_threadfn(void *data) +static int compress_threadfn(void *data) { struct cmp_data *d = data; + unsigned int cmp_len = 0; while (1) { wait_event(d->go, atomic_read_acquire(&d->ready) || @@ -660,9 +675,13 @@ static int lzo_compress_threadfn(void *data) } atomic_set(&d->ready, 0); - d->ret = lzo1x_1_compress(d->unc, d->unc_len, - d->cmp + LZO_HEADER, &d->cmp_len, - d->wrk); + cmp_len = CMP_SIZE - CMP_HEADER; + d->ret = crypto_comp_compress(d->cc, d->unc, d->unc_len, + d->cmp + CMP_HEADER, + &cmp_len); + d->cmp_len = cmp_len; + + atomic_set(&compressed_size, atomic_read(&compressed_size) + d->cmp_len); atomic_set_release(&d->stop, 1); wake_up(&d->done); } @@ -670,14 +689,14 @@ static int lzo_compress_threadfn(void *data) } /** - * save_image_lzo - Save the suspend image data compressed with LZO. + * save_compressed_image - Save the suspend image data after compression. * @handle: Swap map handle to use for saving the image. * @snapshot: Image to read data from. * @nr_to_write: Number of pages to save. */ -static int save_image_lzo(struct swap_map_handle *handle, - struct snapshot_handle *snapshot, - unsigned int nr_to_write) +static int save_compressed_image(struct swap_map_handle *handle, + struct snapshot_handle *snapshot, + unsigned int nr_to_write) { unsigned int m; int ret = 0; @@ -694,23 +713,25 @@ static int save_image_lzo(struct swap_map_handle *handle, hib_init_batch(&hb); + atomic_set(&compressed_size, 0); + /* * We'll limit the number of threads for compression to limit memory * footprint. */ nr_threads = num_online_cpus() - 1; - nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); + nr_threads = clamp_val(nr_threads, 1, CMP_THREADS); page = (void *)__get_free_page(GFP_NOIO | __GFP_HIGH); if (!page) { - pr_err("Failed to allocate LZO page\n"); + pr_err("Failed to allocate %s page\n", hib_comp_algo); ret = -ENOMEM; goto out_clean; } data = vzalloc(array_size(nr_threads, sizeof(*data))); if (!data) { - pr_err("Failed to allocate LZO data\n"); + pr_err("Failed to allocate %s data\n", hib_comp_algo); ret = -ENOMEM; goto out_clean; } @@ -729,7 +750,14 @@ static int save_image_lzo(struct swap_map_handle *handle, init_waitqueue_head(&data[thr].go); init_waitqueue_head(&data[thr].done); - data[thr].thr = kthread_run(lzo_compress_threadfn, + data[thr].cc = crypto_alloc_comp(hib_comp_algo, 0, 0); + if (IS_ERR_OR_NULL(data[thr].cc)) { + pr_err("Could not allocate comp stream %ld\n", PTR_ERR(data[thr].cc)); + ret = -EFAULT; + goto out_clean; + } + + data[thr].thr = kthread_run(compress_threadfn, &data[thr], "image_compress/%u", thr); if (IS_ERR(data[thr].thr)) { @@ -767,7 +795,7 @@ static int save_image_lzo(struct swap_map_handle *handle, */ handle->reqd_free_pages = reqd_free_pages(); - pr_info("Using %u thread(s) for compression\n", nr_threads); + pr_info("Using %u thread(s) for %s compression\n", nr_threads, hib_comp_algo); pr_info("Compressing and saving image data (%u pages)...\n", nr_to_write); m = nr_to_write / 10; @@ -777,7 +805,7 @@ static int save_image_lzo(struct swap_map_handle *handle, start = ktime_get(); for (;;) { for (thr = 0; thr < nr_threads; thr++) { - for (off = 0; off < LZO_UNC_SIZE; off += PAGE_SIZE) { + for (off = 0; off < UNC_SIZE; off += PAGE_SIZE) { ret = snapshot_read_next(snapshot); if (ret < 0) goto out_finish; @@ -817,14 +845,14 @@ static int save_image_lzo(struct swap_map_handle *handle, ret = data[thr].ret; if (ret < 0) { - pr_err("LZO compression failed\n"); + pr_err("%s compression failed\n", hib_comp_algo); goto out_finish; } if (unlikely(!data[thr].cmp_len || data[thr].cmp_len > - lzo1x_worst_compress(data[thr].unc_len))) { - pr_err("Invalid LZO compressed length\n"); + bytes_worst_compress(data[thr].unc_len))) { + pr_err("Invalid %s compressed length\n", hib_comp_algo); ret = -1; goto out_finish; } @@ -840,7 +868,7 @@ static int save_image_lzo(struct swap_map_handle *handle, * read it. */ for (off = 0; - off < LZO_HEADER + data[thr].cmp_len; + off < CMP_HEADER + data[thr].cmp_len; off += PAGE_SIZE) { memcpy(page, data[thr].cmp + off, PAGE_SIZE); @@ -862,6 +890,9 @@ out_finish: if (!ret) pr_info("Image saving done\n"); swsusp_show_speed(start, stop, nr_to_write, "Wrote"); + pr_info("Image size after compression: %d kbytes\n", + (atomic_read(&compressed_size) / 1024)); + out_clean: hib_finish_batch(&hb); if (crc) { @@ -870,9 +901,12 @@ out_clean: kfree(crc); } if (data) { - for (thr = 0; thr < nr_threads; thr++) + for (thr = 0; thr < nr_threads; thr++) { if (data[thr].thr) kthread_stop(data[thr].thr); + if (data[thr].cc) + crypto_free_comp(data[thr].cc); + } vfree(data); } if (page) free_page((unsigned long)page); @@ -942,7 +976,7 @@ int swsusp_write(unsigned int flags) if (!error) { error = (flags & SF_NOCOMPRESS_MODE) ? save_image(&handle, &snapshot, pages - 1) : - save_image_lzo(&handle, &snapshot, pages - 1); + save_compressed_image(&handle, &snapshot, pages - 1); } out_finish: error = swap_writer_finish(&handle, flags, error); @@ -1100,8 +1134,8 @@ static int load_image(struct swap_map_handle *handle, ret = err2; if (!ret) { pr_info("Image loading done\n"); - snapshot_write_finalize(snapshot); - if (!snapshot_image_loaded(snapshot)) + ret = snapshot_write_finalize(snapshot); + if (!ret && !snapshot_image_loaded(snapshot)) ret = -ENODATA; } swsusp_show_speed(start, stop, nr_to_read, "Read"); @@ -1109,10 +1143,11 @@ static int load_image(struct swap_map_handle *handle, } /* - * Structure used for LZO data decompression. + * Structure used for data decompression. */ struct dec_data { struct task_struct *thr; /* thread */ + struct crypto_comp *cc; /* crypto compressor stream */ atomic_t ready; /* ready to start flag */ atomic_t stop; /* ready to stop flag */ int ret; /* return code */ @@ -1120,16 +1155,17 @@ struct dec_data { wait_queue_head_t done; /* decompression done */ size_t unc_len; /* uncompressed length */ size_t cmp_len; /* compressed length */ - unsigned char unc[LZO_UNC_SIZE]; /* uncompressed buffer */ - unsigned char cmp[LZO_CMP_SIZE]; /* compressed buffer */ + unsigned char unc[UNC_SIZE]; /* uncompressed buffer */ + unsigned char cmp[CMP_SIZE]; /* compressed buffer */ }; /* * Decompression function that runs in its own thread. */ -static int lzo_decompress_threadfn(void *data) +static int decompress_threadfn(void *data) { struct dec_data *d = data; + unsigned int unc_len = 0; while (1) { wait_event(d->go, atomic_read_acquire(&d->ready) || @@ -1143,9 +1179,11 @@ static int lzo_decompress_threadfn(void *data) } atomic_set(&d->ready, 0); - d->unc_len = LZO_UNC_SIZE; - d->ret = lzo1x_decompress_safe(d->cmp + LZO_HEADER, d->cmp_len, - d->unc, &d->unc_len); + unc_len = UNC_SIZE; + d->ret = crypto_comp_decompress(d->cc, d->cmp + CMP_HEADER, d->cmp_len, + d->unc, &unc_len); + d->unc_len = unc_len; + if (clean_pages_on_decompress) flush_icache_range((unsigned long)d->unc, (unsigned long)d->unc + d->unc_len); @@ -1157,14 +1195,14 @@ static int lzo_decompress_threadfn(void *data) } /** - * load_image_lzo - Load compressed image data and decompress them with LZO. + * load_compressed_image - Load compressed image data and decompress it. * @handle: Swap map handle to use for loading data. * @snapshot: Image to copy uncompressed data into. * @nr_to_read: Number of pages to load. */ -static int load_image_lzo(struct swap_map_handle *handle, - struct snapshot_handle *snapshot, - unsigned int nr_to_read) +static int load_compressed_image(struct swap_map_handle *handle, + struct snapshot_handle *snapshot, + unsigned int nr_to_read) { unsigned int m; int ret = 0; @@ -1189,18 +1227,18 @@ static int load_image_lzo(struct swap_map_handle *handle, * footprint. */ nr_threads = num_online_cpus() - 1; - nr_threads = clamp_val(nr_threads, 1, LZO_THREADS); + nr_threads = clamp_val(nr_threads, 1, CMP_THREADS); - page = vmalloc(array_size(LZO_MAX_RD_PAGES, sizeof(*page))); + page = vmalloc(array_size(CMP_MAX_RD_PAGES, sizeof(*page))); if (!page) { - pr_err("Failed to allocate LZO page\n"); + pr_err("Failed to allocate %s page\n", hib_comp_algo); ret = -ENOMEM; goto out_clean; } data = vzalloc(array_size(nr_threads, sizeof(*data))); if (!data) { - pr_err("Failed to allocate LZO data\n"); + pr_err("Failed to allocate %s data\n", hib_comp_algo); ret = -ENOMEM; goto out_clean; } @@ -1221,7 +1259,14 @@ static int load_image_lzo(struct swap_map_handle *handle, init_waitqueue_head(&data[thr].go); init_waitqueue_head(&data[thr].done); - data[thr].thr = kthread_run(lzo_decompress_threadfn, + data[thr].cc = crypto_alloc_comp(hib_comp_algo, 0, 0); + if (IS_ERR_OR_NULL(data[thr].cc)) { + pr_err("Could not allocate comp stream %ld\n", PTR_ERR(data[thr].cc)); + ret = -EFAULT; + goto out_clean; + } + + data[thr].thr = kthread_run(decompress_threadfn, &data[thr], "image_decompress/%u", thr); if (IS_ERR(data[thr].thr)) { @@ -1262,18 +1307,18 @@ static int load_image_lzo(struct swap_map_handle *handle, */ if (low_free_pages() > snapshot_get_image_size()) read_pages = (low_free_pages() - snapshot_get_image_size()) / 2; - read_pages = clamp_val(read_pages, LZO_MIN_RD_PAGES, LZO_MAX_RD_PAGES); + read_pages = clamp_val(read_pages, CMP_MIN_RD_PAGES, CMP_MAX_RD_PAGES); for (i = 0; i < read_pages; i++) { - page[i] = (void *)__get_free_page(i < LZO_CMP_PAGES ? + page[i] = (void *)__get_free_page(i < CMP_PAGES ? GFP_NOIO | __GFP_HIGH : GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY); if (!page[i]) { - if (i < LZO_CMP_PAGES) { + if (i < CMP_PAGES) { ring_size = i; - pr_err("Failed to allocate LZO pages\n"); + pr_err("Failed to allocate %s pages\n", hib_comp_algo); ret = -ENOMEM; goto out_clean; } else { @@ -1283,7 +1328,7 @@ static int load_image_lzo(struct swap_map_handle *handle, } want = ring_size = i; - pr_info("Using %u thread(s) for decompression\n", nr_threads); + pr_info("Using %u thread(s) for %s decompression\n", nr_threads, hib_comp_algo); pr_info("Loading and decompressing image data (%u pages)...\n", nr_to_read); m = nr_to_read / 10; @@ -1344,13 +1389,13 @@ static int load_image_lzo(struct swap_map_handle *handle, data[thr].cmp_len = *(size_t *)page[pg]; if (unlikely(!data[thr].cmp_len || data[thr].cmp_len > - lzo1x_worst_compress(LZO_UNC_SIZE))) { - pr_err("Invalid LZO compressed length\n"); + bytes_worst_compress(UNC_SIZE))) { + pr_err("Invalid %s compressed length\n", hib_comp_algo); ret = -1; goto out_finish; } - need = DIV_ROUND_UP(data[thr].cmp_len + LZO_HEADER, + need = DIV_ROUND_UP(data[thr].cmp_len + CMP_HEADER, PAGE_SIZE); if (need > have) { if (eof > 1) { @@ -1361,7 +1406,7 @@ static int load_image_lzo(struct swap_map_handle *handle, } for (off = 0; - off < LZO_HEADER + data[thr].cmp_len; + off < CMP_HEADER + data[thr].cmp_len; off += PAGE_SIZE) { memcpy(data[thr].cmp + off, page[pg], PAGE_SIZE); @@ -1378,7 +1423,7 @@ static int load_image_lzo(struct swap_map_handle *handle, /* * Wait for more data while we are decompressing. */ - if (have < LZO_CMP_PAGES && asked) { + if (have < CMP_PAGES && asked) { ret = hib_wait_io(&hb); if (ret) goto out_finish; @@ -1396,14 +1441,14 @@ static int load_image_lzo(struct swap_map_handle *handle, ret = data[thr].ret; if (ret < 0) { - pr_err("LZO decompression failed\n"); + pr_err("%s decompression failed\n", hib_comp_algo); goto out_finish; } if (unlikely(!data[thr].unc_len || - data[thr].unc_len > LZO_UNC_SIZE || - data[thr].unc_len & (PAGE_SIZE - 1))) { - pr_err("Invalid LZO uncompressed length\n"); + data[thr].unc_len > UNC_SIZE || + data[thr].unc_len & (PAGE_SIZE - 1))) { + pr_err("Invalid %s uncompressed length\n", hib_comp_algo); ret = -1; goto out_finish; } @@ -1441,8 +1486,8 @@ out_finish: stop = ktime_get(); if (!ret) { pr_info("Image loading done\n"); - snapshot_write_finalize(snapshot); - if (!snapshot_image_loaded(snapshot)) + ret = snapshot_write_finalize(snapshot); + if (!ret && !snapshot_image_loaded(snapshot)) ret = -ENODATA; if (!ret) { if (swsusp_header->flags & SF_CRC32_MODE) { @@ -1464,9 +1509,12 @@ out_clean: kfree(crc); } if (data) { - for (thr = 0; thr < nr_threads; thr++) + for (thr = 0; thr < nr_threads; thr++) { if (data[thr].thr) kthread_stop(data[thr].thr); + if (data[thr].cc) + crypto_free_comp(data[thr].cc); + } vfree(data); } vfree(page); @@ -1500,7 +1548,7 @@ int swsusp_read(unsigned int *flags_p) if (!error) { error = (*flags_p & SF_NOCOMPRESS_MODE) ? load_image(&handle, &snapshot, header->pages - 1) : - load_image_lzo(&handle, &snapshot, header->pages - 1); + load_compressed_image(&handle, &snapshot, header->pages - 1); } swap_reader_finish(&handle); end: @@ -1523,10 +1571,10 @@ int swsusp_check(bool exclusive) void *holder = exclusive ? &swsusp_holder : NULL; int error; - hib_resume_bdev_handle = bdev_open_by_dev(swsusp_resume_device, + hib_resume_bdev_file = bdev_file_open_by_dev(swsusp_resume_device, BLK_OPEN_READ, holder, NULL); - if (!IS_ERR(hib_resume_bdev_handle)) { - set_blocksize(hib_resume_bdev_handle->bdev, PAGE_SIZE); + if (!IS_ERR(hib_resume_bdev_file)) { + set_blocksize(file_bdev(hib_resume_bdev_file), PAGE_SIZE); clear_page(swsusp_header); error = hib_submit_io(REQ_OP_READ, swsusp_resume_block, swsusp_header, NULL); @@ -1535,6 +1583,7 @@ int swsusp_check(bool exclusive) if (!memcmp(HIBERNATE_SIG, swsusp_header->sig, 10)) { memcpy(swsusp_header->sig, swsusp_header->orig_sig, 10); + swsusp_header_flags = swsusp_header->flags; /* Reset swap signature now */ error = hib_submit_io(REQ_OP_WRITE | REQ_SYNC, swsusp_resume_block, @@ -1551,11 +1600,11 @@ int swsusp_check(bool exclusive) put: if (error) - bdev_release(hib_resume_bdev_handle); + fput(hib_resume_bdev_file); else pr_debug("Image signature found, resuming\n"); } else { - error = PTR_ERR(hib_resume_bdev_handle); + error = PTR_ERR(hib_resume_bdev_file); } if (error) @@ -1570,12 +1619,12 @@ put: void swsusp_close(void) { - if (IS_ERR(hib_resume_bdev_handle)) { + if (IS_ERR(hib_resume_bdev_file)) { pr_debug("Image device not initialised\n"); return; } - bdev_release(hib_resume_bdev_handle); + fput(hib_resume_bdev_file); } /** diff --git a/kernel/power/user.c b/kernel/power/user.c index 3a4e70366f35..3aa41ba22129 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -317,7 +317,9 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, break; case SNAPSHOT_ATOMIC_RESTORE: - snapshot_write_finalize(&data->handle); + error = snapshot_write_finalize(&data->handle); + if (error) + break; if (data->mode != O_WRONLY || !data->frozen || !snapshot_image_loaded(&data->handle)) { error = -EPERM; diff --git a/kernel/printk/nbcon.c b/kernel/printk/nbcon.c index b96077152f49..c8093bcc01fe 100644 --- a/kernel/printk/nbcon.c +++ b/kernel/printk/nbcon.c @@ -140,39 +140,6 @@ static inline bool nbcon_state_try_cmpxchg(struct console *con, struct nbcon_sta return atomic_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_state), &cur->atom, new->atom); } -#ifdef CONFIG_64BIT - -#define __seq_to_nbcon_seq(seq) (seq) -#define __nbcon_seq_to_seq(seq) (seq) - -#else /* CONFIG_64BIT */ - -#define __seq_to_nbcon_seq(seq) ((u32)seq) - -static inline u64 __nbcon_seq_to_seq(u32 nbcon_seq) -{ - u64 seq; - u64 rb_next_seq; - - /* - * The provided sequence is only the lower 32 bits of the ringbuffer - * sequence. It needs to be expanded to 64bit. Get the next sequence - * number from the ringbuffer and fold it. - * - * Having a 32bit representation in the console is sufficient. - * If a console ever gets more than 2^31 records behind - * the ringbuffer then this is the least of the problems. - * - * Also the access to the ring buffer is always safe. - */ - rb_next_seq = prb_next_seq(prb); - seq = rb_next_seq - ((u32)rb_next_seq - nbcon_seq); - - return seq; -} - -#endif /* CONFIG_64BIT */ - /** * nbcon_seq_read - Read the current console sequence * @con: Console to read the sequence of @@ -183,7 +150,7 @@ u64 nbcon_seq_read(struct console *con) { unsigned long nbcon_seq = atomic_long_read(&ACCESS_PRIVATE(con, nbcon_seq)); - return __nbcon_seq_to_seq(nbcon_seq); + return __ulseq_to_u64seq(prb, nbcon_seq); } /** @@ -204,7 +171,7 @@ void nbcon_seq_force(struct console *con, u64 seq) */ u64 valid_seq = max_t(u64, seq, prb_first_valid_seq(prb)); - atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __seq_to_nbcon_seq(valid_seq)); + atomic_long_set(&ACCESS_PRIVATE(con, nbcon_seq), __u64seq_to_ulseq(valid_seq)); /* Clear con->seq since nbcon consoles use con->nbcon_seq instead. */ con->seq = 0; @@ -223,11 +190,11 @@ void nbcon_seq_force(struct console *con, u64 seq) */ static void nbcon_seq_try_update(struct nbcon_context *ctxt, u64 new_seq) { - unsigned long nbcon_seq = __seq_to_nbcon_seq(ctxt->seq); + unsigned long nbcon_seq = __u64seq_to_ulseq(ctxt->seq); struct console *con = ctxt->console; if (atomic_long_try_cmpxchg(&ACCESS_PRIVATE(con, nbcon_seq), &nbcon_seq, - __seq_to_nbcon_seq(new_seq))) { + __u64seq_to_ulseq(new_seq))) { ctxt->seq = new_seq; } else { ctxt->seq = nbcon_seq_read(con); diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index f2444b581e16..a000bef51177 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -34,7 +34,7 @@ #include <linux/security.h> #include <linux/memblock.h> #include <linux/syscalls.h> -#include <linux/crash_core.h> +#include <linux/vmcore_info.h> #include <linux/ratelimit.h> #include <linux/kmsg_dump.h> #include <linux/syslog.h> @@ -347,6 +347,29 @@ static bool panic_in_progress(void) return unlikely(atomic_read(&panic_cpu) != PANIC_CPU_INVALID); } +/* Return true if a panic is in progress on the current CPU. */ +bool this_cpu_in_panic(void) +{ + /* + * We can use raw_smp_processor_id() here because it is impossible for + * the task to be migrated to the panic_cpu, or away from it. If + * panic_cpu has already been set, and we're not currently executing on + * that CPU, then we never will be. + */ + return unlikely(atomic_read(&panic_cpu) == raw_smp_processor_id()); +} + +/* + * Return true if a panic is in progress on a remote CPU. + * + * On true, the local CPU should immediately release any printing resources + * that may be needed by the panic CPU. + */ +bool other_cpu_in_panic(void) +{ + return (panic_in_progress() && !this_cpu_in_panic()); +} + /* * This is used for debugging the mess that is the VT code by * keeping track if we have the console semaphore held. It's @@ -439,12 +462,6 @@ static int console_msg_format = MSG_FORMAT_DEFAULT; static DEFINE_MUTEX(syslog_lock); #ifdef CONFIG_PRINTK -/* - * During panic, heavy printk by other CPUs can delay the - * panic and risk deadlock on console resources. - */ -static int __read_mostly suppress_panic_printk; - DECLARE_WAIT_QUEUE_HEAD(log_wait); /* All 3 protected by @syslog_lock. */ /* the next printk record to read by syslog(READ) or /proc/kmsg */ @@ -598,17 +615,6 @@ static int check_syslog_permissions(int type, int source) if (syslog_action_restricted(type)) { if (capable(CAP_SYSLOG)) goto ok; - /* - * For historical reasons, accept CAP_SYS_ADMIN too, with - * a warning. - */ - if (capable(CAP_SYS_ADMIN)) { - pr_warn_once("%s (%d): Attempt to access syslog with " - "CAP_SYS_ADMIN but no CAP_SYSLOG " - "(deprecated).\n", - current->comm, task_pid_nr(current)); - goto ok; - } return -EPERM; } ok: @@ -951,7 +957,7 @@ const struct file_operations kmsg_fops = { .release = devkmsg_release, }; -#ifdef CONFIG_CRASH_CORE +#ifdef CONFIG_VMCORE_INFO /* * This appends the listed symbols to /proc/vmcore * @@ -1846,10 +1852,23 @@ static bool console_waiter; */ static void console_lock_spinning_enable(void) { + /* + * Do not use spinning in panic(). The panic CPU wants to keep the lock. + * Non-panic CPUs abandon the flush anyway. + * + * Just keep the lockdep annotation. The panic-CPU should avoid + * taking console_owner_lock because it might cause a deadlock. + * This looks like the easiest way how to prevent false lockdep + * reports without handling races a lockless way. + */ + if (panic_in_progress()) + goto lockdep; + raw_spin_lock(&console_owner_lock); console_owner = current; raw_spin_unlock(&console_owner_lock); +lockdep: /* The waiter may spin on us after setting console_owner */ spin_acquire(&console_owner_dep_map, 0, 0, _THIS_IP_); } @@ -1874,6 +1893,22 @@ static int console_lock_spinning_disable_and_check(int cookie) { int waiter; + /* + * Ignore spinning waiters during panic() because they might get stopped + * or blocked at any time, + * + * It is safe because nobody is allowed to start spinning during panic + * in the first place. If there has been a waiter then non panic CPUs + * might stay spinning. They would get stopped anyway. The panic context + * will never start spinning and an interrupted spin on panic CPU will + * never continue. + */ + if (panic_in_progress()) { + /* Keep lockdep happy. */ + spin_release(&console_owner_dep_map, _THIS_IP_); + return 0; + } + raw_spin_lock(&console_owner_lock); waiter = READ_ONCE(console_waiter); console_owner = NULL; @@ -2270,8 +2305,12 @@ asmlinkage int vprintk_emit(int facility, int level, if (unlikely(suppress_printk)) return 0; - if (unlikely(suppress_panic_printk) && - atomic_read(&panic_cpu) != raw_smp_processor_id()) + /* + * The messages on the panic CPU are the most important. If + * non-panic CPUs are generating any messages, they will be + * silently dropped. + */ + if (other_cpu_in_panic()) return 0; if (level == LOGLEVEL_SCHED) { @@ -2601,26 +2640,6 @@ static int console_cpu_notify(unsigned int cpu) return 0; } -/* - * Return true if a panic is in progress on a remote CPU. - * - * On true, the local CPU should immediately release any printing resources - * that may be needed by the panic CPU. - */ -bool other_cpu_in_panic(void) -{ - if (!panic_in_progress()) - return false; - - /* - * We can use raw_smp_processor_id() here because it is impossible for - * the task to be migrated to the panic_cpu, or away from it. If - * panic_cpu has already been set, and we're not currently executing on - * that CPU, then we never will be. - */ - return atomic_read(&panic_cpu) != raw_smp_processor_id(); -} - /** * console_lock - block the console subsystem from printing * @@ -2776,8 +2795,6 @@ void console_prepend_dropped(struct printk_message *pmsg, unsigned long dropped) bool printk_get_next_message(struct printk_message *pmsg, u64 seq, bool is_extended, bool may_suppress) { - static int panic_console_dropped; - struct printk_buffers *pbufs = pmsg->pbufs; const size_t scratchbuf_sz = sizeof(pbufs->scratchbuf); const size_t outbuf_sz = sizeof(pbufs->outbuf); @@ -2805,17 +2822,6 @@ bool printk_get_next_message(struct printk_message *pmsg, u64 seq, pmsg->seq = r.info->seq; pmsg->dropped = r.info->seq - seq; - /* - * Check for dropped messages in panic here so that printk - * suppression can occur as early as possible if necessary. - */ - if (pmsg->dropped && - panic_in_progress() && - panic_console_dropped++ > 10) { - suppress_panic_printk = 1; - pr_warn_once("Too many dropped messages. Suppress messages on non-panic CPUs to prevent livelock.\n"); - } - /* Skip record that has level above the console loglevel. */ if (may_suppress && suppress_message_printing(r.info->level)) goto out; @@ -3761,7 +3767,7 @@ static bool __pr_flush(struct console *con, int timeout_ms, bool reset_on_progre might_sleep(); - seq = prb_next_seq(prb); + seq = prb_next_reserve_seq(prb); /* Flush the consoles so that records up to @seq are printed. */ console_lock(); diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c index fde338606ce8..88e8f3a61922 100644 --- a/kernel/printk/printk_ringbuffer.c +++ b/kernel/printk/printk_ringbuffer.c @@ -6,6 +6,7 @@ #include <linux/errno.h> #include <linux/bug.h> #include "printk_ringbuffer.h" +#include "internal.h" /** * DOC: printk_ringbuffer overview @@ -303,6 +304,9 @@ * * desc_push_tail:B / desc_reserve:D * set descriptor reusable (state), then push descriptor tail (id) + * + * desc_update_last_finalized:A / desc_last_finalized_seq:A + * store finalized record, then set new highest finalized sequence number */ #define DATA_SIZE(data_ring) _DATA_SIZE((data_ring)->size_bits) @@ -1030,9 +1034,13 @@ static char *data_alloc(struct printk_ringbuffer *rb, unsigned int size, unsigned long next_lpos; if (size == 0) { - /* Specify a data-less block. */ - blk_lpos->begin = NO_LPOS; - blk_lpos->next = NO_LPOS; + /* + * Data blocks are not created for empty lines. Instead, the + * reader will recognize these special lpos values and handle + * it appropriately. + */ + blk_lpos->begin = EMPTY_LINE_LPOS; + blk_lpos->next = EMPTY_LINE_LPOS; return NULL; } @@ -1210,10 +1218,18 @@ static const char *get_data(struct prb_data_ring *data_ring, /* Data-less data block description. */ if (BLK_DATALESS(blk_lpos)) { - if (blk_lpos->begin == NO_LPOS && blk_lpos->next == NO_LPOS) { + /* + * Records that are just empty lines are also valid, even + * though they do not have a data block. For such records + * explicitly return empty string data to signify success. + */ + if (blk_lpos->begin == EMPTY_LINE_LPOS && + blk_lpos->next == EMPTY_LINE_LPOS) { *data_size = 0; return ""; } + + /* Data lost, invalid, or otherwise unavailable. */ return NULL; } @@ -1442,19 +1458,117 @@ fail_reopen: } /* + * @last_finalized_seq value guarantees that all records up to and including + * this sequence number are finalized and can be read. The only exception are + * too old records which have already been overwritten. + * + * It is also guaranteed that @last_finalized_seq only increases. + * + * Be aware that finalized records following non-finalized records are not + * reported because they are not yet available to the reader. For example, + * a new record stored via printk() will not be available to a printer if + * it follows a record that has not been finalized yet. However, once that + * non-finalized record becomes finalized, @last_finalized_seq will be + * appropriately updated and the full set of finalized records will be + * available to the printer. And since each printk() caller will either + * directly print or trigger deferred printing of all available unprinted + * records, all printk() messages will get printed. + */ +static u64 desc_last_finalized_seq(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + unsigned long ulseq; + + /* + * Guarantee the sequence number is loaded before loading the + * associated record in order to guarantee that the record can be + * seen by this CPU. This pairs with desc_update_last_finalized:A. + */ + ulseq = atomic_long_read_acquire(&desc_ring->last_finalized_seq + ); /* LMM(desc_last_finalized_seq:A) */ + + return __ulseq_to_u64seq(rb, ulseq); +} + +static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, + struct printk_record *r, unsigned int *line_count); + +/* + * Check if there are records directly following @last_finalized_seq that are + * finalized. If so, update @last_finalized_seq to the latest of these + * records. It is not allowed to skip over records that are not yet finalized. + */ +static void desc_update_last_finalized(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + u64 old_seq = desc_last_finalized_seq(rb); + unsigned long oldval; + unsigned long newval; + u64 finalized_seq; + u64 try_seq; + +try_again: + finalized_seq = old_seq; + try_seq = finalized_seq + 1; + + /* Try to find later finalized records. */ + while (_prb_read_valid(rb, &try_seq, NULL, NULL)) { + finalized_seq = try_seq; + try_seq++; + } + + /* No update needed if no later finalized record was found. */ + if (finalized_seq == old_seq) + return; + + oldval = __u64seq_to_ulseq(old_seq); + newval = __u64seq_to_ulseq(finalized_seq); + + /* + * Set the sequence number of a later finalized record that has been + * seen. + * + * Guarantee the record data is visible to other CPUs before storing + * its sequence number. This pairs with desc_last_finalized_seq:A. + * + * Memory barrier involvement: + * + * If desc_last_finalized_seq:A reads from + * desc_update_last_finalized:A, then desc_read:A reads from + * _prb_commit:B. + * + * Relies on: + * + * RELEASE from _prb_commit:B to desc_update_last_finalized:A + * matching + * ACQUIRE from desc_last_finalized_seq:A to desc_read:A + * + * Note: _prb_commit:B and desc_update_last_finalized:A can be + * different CPUs. However, the desc_update_last_finalized:A + * CPU (which performs the release) must have previously seen + * _prb_commit:B. + */ + if (!atomic_long_try_cmpxchg_release(&desc_ring->last_finalized_seq, + &oldval, newval)) { /* LMM(desc_update_last_finalized:A) */ + old_seq = __ulseq_to_u64seq(rb, oldval); + goto try_again; + } +} + +/* * Attempt to finalize a specified descriptor. If this fails, the descriptor * is either already final or it will finalize itself when the writer commits. */ -static void desc_make_final(struct prb_desc_ring *desc_ring, unsigned long id) +static void desc_make_final(struct printk_ringbuffer *rb, unsigned long id) { + struct prb_desc_ring *desc_ring = &rb->desc_ring; unsigned long prev_state_val = DESC_SV(id, desc_committed); struct prb_desc *d = to_desc(desc_ring, id); - atomic_long_cmpxchg_relaxed(&d->state_var, prev_state_val, - DESC_SV(id, desc_finalized)); /* LMM(desc_make_final:A) */ - - /* Best effort to remember the last finalized @id. */ - atomic_long_set(&desc_ring->last_finalized_id, id); + if (atomic_long_try_cmpxchg_relaxed(&d->state_var, &prev_state_val, + DESC_SV(id, desc_finalized))) { /* LMM(desc_make_final:A) */ + desc_update_last_finalized(rb); + } } /** @@ -1550,7 +1664,7 @@ bool prb_reserve(struct prb_reserved_entry *e, struct printk_ringbuffer *rb, * readers. (For seq==0 there is no previous descriptor.) */ if (info->seq > 0) - desc_make_final(desc_ring, DESC_ID(id - 1)); + desc_make_final(rb, DESC_ID(id - 1)); r->text_buf = data_alloc(rb, r->text_buf_size, &d->text_blk_lpos, id); /* If text data allocation fails, a data-less record is committed. */ @@ -1643,7 +1757,7 @@ void prb_commit(struct prb_reserved_entry *e) */ head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_commit:A) */ if (head_id != e->id) - desc_make_final(desc_ring, e->id); + desc_make_final(e->rb, e->id); } /** @@ -1663,12 +1777,9 @@ void prb_commit(struct prb_reserved_entry *e) */ void prb_final_commit(struct prb_reserved_entry *e) { - struct prb_desc_ring *desc_ring = &e->rb->desc_ring; - _prb_commit(e, desc_finalized); - /* Best effort to remember the last finalized @id. */ - atomic_long_set(&desc_ring->last_finalized_id, e->id); + desc_update_last_finalized(e->rb); } /* @@ -1832,7 +1943,7 @@ static int prb_read(struct printk_ringbuffer *rb, u64 seq, } /* Get the sequence number of the tail descriptor. */ -static u64 prb_first_seq(struct printk_ringbuffer *rb) +u64 prb_first_seq(struct printk_ringbuffer *rb) { struct prb_desc_ring *desc_ring = &rb->desc_ring; enum desc_state d_state; @@ -1875,12 +1986,123 @@ static u64 prb_first_seq(struct printk_ringbuffer *rb) return seq; } +/** + * prb_next_reserve_seq() - Get the sequence number after the most recently + * reserved record. + * + * @rb: The ringbuffer to get the sequence number from. + * + * This is the public function available to readers to see what sequence + * number will be assigned to the next reserved record. + * + * Note that depending on the situation, this value can be equal to or + * higher than the sequence number returned by prb_next_seq(). + * + * Context: Any context. + * Return: The sequence number that will be assigned to the next record + * reserved. + */ +u64 prb_next_reserve_seq(struct printk_ringbuffer *rb) +{ + struct prb_desc_ring *desc_ring = &rb->desc_ring; + unsigned long last_finalized_id; + atomic_long_t *state_var; + u64 last_finalized_seq; + unsigned long head_id; + struct prb_desc desc; + unsigned long diff; + struct prb_desc *d; + int err; + + /* + * It may not be possible to read a sequence number for @head_id. + * So the ID of @last_finailzed_seq is used to calculate what the + * sequence number of @head_id will be. + */ + +try_again: + last_finalized_seq = desc_last_finalized_seq(rb); + + /* + * @head_id is loaded after @last_finalized_seq to ensure that + * it points to the record with @last_finalized_seq or newer. + * + * Memory barrier involvement: + * + * If desc_last_finalized_seq:A reads from + * desc_update_last_finalized:A, then + * prb_next_reserve_seq:A reads from desc_reserve:D. + * + * Relies on: + * + * RELEASE from desc_reserve:D to desc_update_last_finalized:A + * matching + * ACQUIRE from desc_last_finalized_seq:A to prb_next_reserve_seq:A + * + * Note: desc_reserve:D and desc_update_last_finalized:A can be + * different CPUs. However, the desc_update_last_finalized:A CPU + * (which performs the release) must have previously seen + * desc_read:C, which implies desc_reserve:D can be seen. + */ + head_id = atomic_long_read(&desc_ring->head_id); /* LMM(prb_next_reserve_seq:A) */ + + d = to_desc(desc_ring, last_finalized_seq); + state_var = &d->state_var; + + /* Extract the ID, used to specify the descriptor to read. */ + last_finalized_id = DESC_ID(atomic_long_read(state_var)); + + /* Ensure @last_finalized_id is correct. */ + err = desc_read_finalized_seq(desc_ring, last_finalized_id, last_finalized_seq, &desc); + + if (err == -EINVAL) { + if (last_finalized_seq == 0) { + /* + * No record has been finalized or even reserved yet. + * + * The @head_id is initialized such that the first + * increment will yield the first record (seq=0). + * Handle it separately to avoid a negative @diff + * below. + */ + if (head_id == DESC0_ID(desc_ring->count_bits)) + return 0; + + /* + * One or more descriptors are already reserved. Use + * the descriptor ID of the first one (@seq=0) for + * the @diff below. + */ + last_finalized_id = DESC0_ID(desc_ring->count_bits) + 1; + } else { + /* Record must have been overwritten. Try again. */ + goto try_again; + } + } + + /* Diff of known descriptor IDs to compute related sequence numbers. */ + diff = head_id - last_finalized_id; + + /* + * @head_id points to the most recently reserved record, but this + * function returns the sequence number that will be assigned to the + * next (not yet reserved) record. Thus +1 is needed. + */ + return (last_finalized_seq + diff + 1); +} + /* - * Non-blocking read of a record. Updates @seq to the last finalized record - * (which may have no data available). + * Non-blocking read of a record. + * + * On success @seq is updated to the record that was read and (if provided) + * @r and @line_count will contain the read/calculated data. + * + * On failure @seq is updated to a record that is not yet available to the + * reader, but it will be the next record available to the reader. * - * See the description of prb_read_valid() and prb_read_valid_info() - * for details. + * Note: When the current CPU is in panic, this function will skip over any + * non-existent/non-finalized records in order to allow the panic CPU + * to print any and all records that have been finalized. */ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, struct printk_record *r, unsigned int *line_count) @@ -1899,12 +2121,32 @@ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, *seq = tail_seq; } else if (err == -ENOENT) { - /* Record exists, but no data available. Skip. */ + /* Record exists, but the data was lost. Skip. */ (*seq)++; } else { - /* Non-existent/non-finalized record. Must stop. */ - return false; + /* + * Non-existent/non-finalized record. Must stop. + * + * For panic situations it cannot be expected that + * non-finalized records will become finalized. But + * there may be other finalized records beyond that + * need to be printed for a panic situation. If this + * is the panic CPU, skip this + * non-existent/non-finalized record unless it is + * at or beyond the head, in which case it is not + * possible to continue. + * + * Note that new messages printed on panic CPU are + * finalized when we are here. The only exception + * might be the last message without trailing newline. + * But it would have the sequence number returned + * by "prb_next_reserve_seq() - 1". + */ + if (this_cpu_in_panic() && ((*seq + 1) < prb_next_reserve_seq(rb))) + (*seq)++; + else + return false; } } @@ -1932,7 +2174,7 @@ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq, * On success, the reader must check r->info.seq to see which record was * actually read. This allows the reader to detect dropped records. * - * Failure means @seq refers to a not yet written record. + * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, struct printk_record *r) @@ -1962,7 +2204,7 @@ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, * On success, the reader must check info->seq to see which record meta data * was actually read. This allows the reader to detect dropped records. * - * Failure means @seq refers to a not yet written record. + * Failure means @seq refers to a record not yet available to the reader. */ bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count) @@ -2008,7 +2250,9 @@ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) * newest sequence number available to readers will be. * * This provides readers a sequence number to jump to if all currently - * available records should be skipped. + * available records should be skipped. It is guaranteed that all records + * previous to the returned value have been finalized and are (or were) + * available to the reader. * * Context: Any context. * Return: The sequence number of the next newest (not yet available) record @@ -2016,34 +2260,19 @@ u64 prb_first_valid_seq(struct printk_ringbuffer *rb) */ u64 prb_next_seq(struct printk_ringbuffer *rb) { - struct prb_desc_ring *desc_ring = &rb->desc_ring; - enum desc_state d_state; - unsigned long id; u64 seq; - /* Check if the cached @id still points to a valid @seq. */ - id = atomic_long_read(&desc_ring->last_finalized_id); - d_state = desc_read(desc_ring, id, NULL, &seq, NULL); + seq = desc_last_finalized_seq(rb); - if (d_state == desc_finalized || d_state == desc_reusable) { - /* - * Begin searching after the last finalized record. - * - * On 0, the search must begin at 0 because of hack#2 - * of the bootstrapping phase it is not known if a - * record at index 0 exists. - */ - if (seq != 0) - seq++; - } else { - /* - * The information about the last finalized sequence number - * has gone. It should happen only when there is a flood of - * new messages and the ringbuffer is rapidly recycled. - * Give up and start from the beginning. - */ - seq = 0; - } + /* + * Begin searching after the last finalized record. + * + * On 0, the search must begin at 0 because of hack#2 + * of the bootstrapping phase it is not known if a + * record at index 0 exists. + */ + if (seq != 0) + seq++; /* * The information about the last finalized @seq might be inaccurate. @@ -2085,7 +2314,7 @@ void prb_init(struct printk_ringbuffer *rb, rb->desc_ring.infos = infos; atomic_long_set(&rb->desc_ring.head_id, DESC0_ID(descbits)); atomic_long_set(&rb->desc_ring.tail_id, DESC0_ID(descbits)); - atomic_long_set(&rb->desc_ring.last_finalized_id, DESC0_ID(descbits)); + atomic_long_set(&rb->desc_ring.last_finalized_seq, 0); rb->text_data_ring.size_bits = textbits; rb->text_data_ring.data = text_buf; diff --git a/kernel/printk/printk_ringbuffer.h b/kernel/printk/printk_ringbuffer.h index 18cd25e489b8..52626d0f1fa3 100644 --- a/kernel/printk/printk_ringbuffer.h +++ b/kernel/printk/printk_ringbuffer.h @@ -75,7 +75,7 @@ struct prb_desc_ring { struct printk_info *infos; atomic_long_t head_id; atomic_long_t tail_id; - atomic_long_t last_finalized_id; + atomic_long_t last_finalized_seq; }; /* @@ -127,8 +127,22 @@ enum desc_state { #define DESC_SV(id, state) (((unsigned long)state << DESC_FLAGS_SHIFT) | id) #define DESC_ID_MASK (~DESC_FLAGS_MASK) #define DESC_ID(sv) ((sv) & DESC_ID_MASK) + +/* + * Special data block logical position values (for fields of + * @prb_desc.text_blk_lpos). + * + * - Bit0 is used to identify if the record has no data block. (Implemented in + * the LPOS_DATALESS() macro.) + * + * - Bit1 specifies the reason for not having a data block. + * + * These special values could never be real lpos values because of the + * meta data and alignment padding of data blocks. (See to_blk_size() for + * details.) + */ #define FAILED_LPOS 0x1 -#define NO_LPOS 0x3 +#define EMPTY_LINE_LPOS 0x3 #define FAILED_BLK_LPOS \ { \ @@ -259,7 +273,7 @@ static struct printk_ringbuffer name = { \ .infos = &_##name##_infos[0], \ .head_id = ATOMIC_INIT(DESC0_ID(descbits)), \ .tail_id = ATOMIC_INIT(DESC0_ID(descbits)), \ - .last_finalized_id = ATOMIC_INIT(DESC0_ID(descbits)), \ + .last_finalized_seq = ATOMIC_INIT(0), \ }, \ .text_data_ring = { \ .size_bits = (avgtextbits) + (descbits), \ @@ -378,7 +392,41 @@ bool prb_read_valid(struct printk_ringbuffer *rb, u64 seq, bool prb_read_valid_info(struct printk_ringbuffer *rb, u64 seq, struct printk_info *info, unsigned int *line_count); +u64 prb_first_seq(struct printk_ringbuffer *rb); u64 prb_first_valid_seq(struct printk_ringbuffer *rb); u64 prb_next_seq(struct printk_ringbuffer *rb); +u64 prb_next_reserve_seq(struct printk_ringbuffer *rb); + +#ifdef CONFIG_64BIT + +#define __u64seq_to_ulseq(u64seq) (u64seq) +#define __ulseq_to_u64seq(rb, ulseq) (ulseq) + +#else /* CONFIG_64BIT */ + +#define __u64seq_to_ulseq(u64seq) ((u32)u64seq) + +static inline u64 __ulseq_to_u64seq(struct printk_ringbuffer *rb, u32 ulseq) +{ + u64 rb_first_seq = prb_first_seq(rb); + u64 seq; + + /* + * The provided sequence is only the lower 32 bits of the ringbuffer + * sequence. It needs to be expanded to 64bit. Get the first sequence + * number from the ringbuffer and fold it. + * + * Having a 32bit representation in the console is sufficient. + * If a console ever gets more than 2^31 records behind + * the ringbuffer then this is the least of the problems. + * + * Also the access to the ring buffer is always safe. + */ + seq = rb_first_seq - (s32)((u32)rb_first_seq - ulseq); + + return seq; +} + +#endif /* CONFIG_64BIT */ #endif /* _KERNEL_PRINTK_RINGBUFFER_H */ diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 2fabd497d659..d5f89f9ef29f 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -375,10 +375,13 @@ static int check_ptrace_options(unsigned long data) return 0; } -static inline void ptrace_set_stopped(struct task_struct *task) +static inline void ptrace_set_stopped(struct task_struct *task, bool seize) { guard(spinlock)(&task->sighand->siglock); + /* SEIZE doesn't trap tracee on attach */ + if (!seize) + send_signal_locked(SIGSTOP, SEND_SIG_PRIV, task, PIDTYPE_PID); /* * If the task is already STOPPED, set JOBCTL_TRAP_STOP and * TRAPPING, and kick it so that it transits to TRACED. TRAPPING @@ -457,14 +460,8 @@ static int ptrace_attach(struct task_struct *task, long request, return -EPERM; task->ptrace = flags; - ptrace_link(task, current); - - /* SEIZE doesn't trap tracee on attach */ - if (!seize) - send_sig_info(SIGSTOP, SEND_SIG_PRIV, task); - - ptrace_set_stopped(task); + ptrace_set_stopped(task, seize); } } diff --git a/kernel/rcu/Kconfig b/kernel/rcu/Kconfig index bdd7eadb33d8..e7d2dd267593 100644 --- a/kernel/rcu/Kconfig +++ b/kernel/rcu/Kconfig @@ -314,6 +314,19 @@ config RCU_LAZY To save power, batch RCU callbacks and flush after delay, memory pressure, or callback list growing too big. + Requires rcu_nocbs=all to be set. + + Use rcutree.enable_rcu_lazy=0 to turn it off at boot time. + +config RCU_LAZY_DEFAULT_OFF + bool "Turn RCU lazy invocation off by default" + depends on RCU_LAZY + default n + help + Allows building the kernel with CONFIG_RCU_LAZY=y yet keep it default + off. Boot time param rcutree.enable_rcu_lazy=1 can be used to switch + it back on. + config RCU_DOUBLE_CHECK_CB_TIME bool "RCU callback-batch backup time check" depends on RCU_EXPERT diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h index f94f65877f2b..86fce206560e 100644 --- a/kernel/rcu/rcu.h +++ b/kernel/rcu/rcu.h @@ -528,6 +528,12 @@ struct task_struct *get_rcu_tasks_gp_kthread(void); struct task_struct *get_rcu_tasks_rude_gp_kthread(void); #endif // # ifdef CONFIG_TASKS_RUDE_RCU +#ifdef CONFIG_TASKS_RCU_GENERIC +void tasks_cblist_init_generic(void); +#else /* #ifdef CONFIG_TASKS_RCU_GENERIC */ +static inline void tasks_cblist_init_generic(void) { } +#endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */ + #define RCU_SCHEDULER_INACTIVE 0 #define RCU_SCHEDULER_INIT 1 #define RCU_SCHEDULER_RUNNING 2 @@ -543,11 +549,11 @@ enum rcutorture_type { }; #if defined(CONFIG_RCU_LAZY) -unsigned long rcu_lazy_get_jiffies_till_flush(void); -void rcu_lazy_set_jiffies_till_flush(unsigned long j); +unsigned long rcu_get_jiffies_lazy_flush(void); +void rcu_set_jiffies_lazy_flush(unsigned long j); #else -static inline unsigned long rcu_lazy_get_jiffies_till_flush(void) { return 0; } -static inline void rcu_lazy_set_jiffies_till_flush(unsigned long j) { } +static inline unsigned long rcu_get_jiffies_lazy_flush(void) { return 0; } +static inline void rcu_set_jiffies_lazy_flush(unsigned long j) { } #endif #if defined(CONFIG_TREE_RCU) @@ -623,12 +629,7 @@ int rcu_get_gp_kthreads_prio(void); void rcu_fwd_progress_check(unsigned long j); void rcu_force_quiescent_state(void); extern struct workqueue_struct *rcu_gp_wq; -#ifdef CONFIG_RCU_EXP_KTHREAD extern struct kthread_worker *rcu_exp_gp_kworker; -extern struct kthread_worker *rcu_exp_par_gp_kworker; -#else /* !CONFIG_RCU_EXP_KTHREAD */ -extern struct workqueue_struct *rcu_par_gp_wq; -#endif /* CONFIG_RCU_EXP_KTHREAD */ void rcu_gp_slow_register(atomic_t *rgssp); void rcu_gp_slow_unregister(atomic_t *rgssp); #endif /* #else #ifdef CONFIG_TINY_RCU */ diff --git a/kernel/rcu/rcuscale.c b/kernel/rcu/rcuscale.c index ffdb30495e3c..8db4fedaaa1e 100644 --- a/kernel/rcu/rcuscale.c +++ b/kernel/rcu/rcuscale.c @@ -764,9 +764,9 @@ kfree_scale_init(void) if (kfree_by_call_rcu) { /* do a test to check the timeout. */ - orig_jif = rcu_lazy_get_jiffies_till_flush(); + orig_jif = rcu_get_jiffies_lazy_flush(); - rcu_lazy_set_jiffies_till_flush(2 * HZ); + rcu_set_jiffies_lazy_flush(2 * HZ); rcu_barrier(); jif_start = jiffies; @@ -775,7 +775,7 @@ kfree_scale_init(void) smp_cond_load_relaxed(&rcu_lazy_test1_cb_called, VAL == 1); - rcu_lazy_set_jiffies_till_flush(orig_jif); + rcu_set_jiffies_lazy_flush(orig_jif); if (WARN_ON_ONCE(jiffies_at_lazy_cb - jif_start < 2 * HZ)) { pr_alert("ERROR: call_rcu() CBs are not being lazy as expected!\n"); diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c index 7567ca8e743c..45d6b4c3d199 100644 --- a/kernel/rcu/rcutorture.c +++ b/kernel/rcu/rcutorture.c @@ -1368,9 +1368,13 @@ rcu_torture_writer(void *arg) struct rcu_torture *rp; struct rcu_torture *old_rp; static DEFINE_TORTURE_RANDOM(rand); + unsigned long stallsdone = jiffies; bool stutter_waited; unsigned long ulo[NUM_ACTIVE_RCU_POLL_OLDSTATE]; + // If a new stall test is added, this must be adjusted. + if (stall_cpu_holdoff + stall_gp_kthread + stall_cpu) + stallsdone += (stall_cpu_holdoff + stall_gp_kthread + stall_cpu + 60) * HZ; VERBOSE_TOROUT_STRING("rcu_torture_writer task started"); if (!can_expedite) pr_alert("%s" TORTURE_FLAG @@ -1576,11 +1580,11 @@ rcu_torture_writer(void *arg) !atomic_read(&rcu_fwd_cb_nodelay) && !cur_ops->slow_gps && !torture_must_stop() && - boot_ended) + boot_ended && + time_after(jiffies, stallsdone)) for (i = 0; i < ARRAY_SIZE(rcu_tortures); i++) if (list_empty(&rcu_tortures[i].rtort_free) && - rcu_access_pointer(rcu_torture_current) != - &rcu_tortures[i]) { + rcu_access_pointer(rcu_torture_current) != &rcu_tortures[i]) { tracing_off(); show_rcu_gp_kthreads(); WARN(1, "%s: rtort_pipe_count: %d\n", __func__, rcu_tortures[i].rtort_pipe_count); @@ -2441,7 +2445,8 @@ static struct notifier_block rcu_torture_stall_block = { /* * CPU-stall kthread. It waits as specified by stall_cpu_holdoff, then - * induces a CPU stall for the time specified by stall_cpu. + * induces a CPU stall for the time specified by stall_cpu. If a new + * stall test is added, stallsdone in rcu_torture_writer() must be adjusted. */ static int rcu_torture_stall(void *args) { diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c index 0351a4e83529..e4d673fc30f4 100644 --- a/kernel/rcu/srcutree.c +++ b/kernel/rcu/srcutree.c @@ -1234,11 +1234,20 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, if (rhp) rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp); /* - * The snapshot for acceleration must be taken _before_ the read of the - * current gp sequence used for advancing, otherwise advancing may fail - * and acceleration may then fail too. + * It's crucial to capture the snapshot 's' for acceleration before + * reading the current gp_seq that is used for advancing. This is + * essential because if the acceleration snapshot is taken after a + * failed advancement attempt, there's a risk that a grace period may + * conclude and a new one may start in the interim. If the snapshot is + * captured after this sequence of events, the acceleration snapshot 's' + * could be excessively advanced, leading to acceleration failure. + * In such a scenario, an 'acceleration leak' can occur, where new + * callbacks become indefinitely stuck in the RCU_NEXT_TAIL segment. + * Also note that encountering advancing failures is a normal + * occurrence when the grace period for RCU_WAIT_TAIL is in progress. * - * This could happen if: + * To see this, consider the following events which occur if + * rcu_seq_snap() were to be called after advance: * * 1) The RCU_WAIT_TAIL segment has callbacks (gp_num = X + 4) and the * RCU_NEXT_READY_TAIL also has callbacks (gp_num = X + 8). @@ -1264,6 +1273,13 @@ static unsigned long srcu_gp_start_if_needed(struct srcu_struct *ssp, if (rhp) { rcu_segcblist_advance(&sdp->srcu_cblist, rcu_seq_current(&ssp->srcu_sup->srcu_gp_seq)); + /* + * Acceleration can never fail because the base current gp_seq + * used for acceleration is <= the value of gp_seq used for + * advancing. This means that RCU_NEXT_TAIL segment will + * always be able to be emptied by the acceleration into the + * RCU_NEXT_READY_TAIL or RCU_WAIT_TAIL segments. + */ WARN_ON_ONCE(!rcu_segcblist_accelerate(&sdp->srcu_cblist, s)); } if (ULONG_CMP_LT(sdp->srcu_gp_seq_needed, s)) { diff --git a/kernel/rcu/sync.c b/kernel/rcu/sync.c index e550f97779b8..86df878a2fee 100644 --- a/kernel/rcu/sync.c +++ b/kernel/rcu/sync.c @@ -24,22 +24,6 @@ void rcu_sync_init(struct rcu_sync *rsp) init_waitqueue_head(&rsp->gp_wait); } -/** - * rcu_sync_enter_start - Force readers onto slow path for multiple updates - * @rsp: Pointer to rcu_sync structure to use for synchronization - * - * Must be called after rcu_sync_init() and before first use. - * - * Ensures rcu_sync_is_idle() returns false and rcu_sync_{enter,exit}() - * pairs turn into NO-OPs. - */ -void rcu_sync_enter_start(struct rcu_sync *rsp) -{ - rsp->gp_count++; - rsp->gp_state = GP_PASSED; -} - - static void rcu_sync_func(struct rcu_head *rhp); static void rcu_sync_call(struct rcu_sync *rsp) diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 732ad5b39946..147b5945d67a 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -32,6 +32,7 @@ typedef void (*postgp_func_t)(struct rcu_tasks *rtp); * @rtp_irq_work: IRQ work queue for deferred wakeups. * @barrier_q_head: RCU callback for barrier operation. * @rtp_blkd_tasks: List of tasks blocked as readers. + * @rtp_exit_list: List of tasks in the latter portion of do_exit(). * @cpu: CPU number corresponding to this entry. * @rtpp: Pointer to the rcu_tasks structure. */ @@ -46,6 +47,7 @@ struct rcu_tasks_percpu { struct irq_work rtp_irq_work; struct rcu_head barrier_q_head; struct list_head rtp_blkd_tasks; + struct list_head rtp_exit_list; int cpu; struct rcu_tasks *rtpp; }; @@ -144,8 +146,6 @@ static struct rcu_tasks rt_name = \ } #ifdef CONFIG_TASKS_RCU -/* Track exiting tasks in order to allow them to be waited for. */ -DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu); /* Report delay in synchronize_srcu() completion in rcu_tasks_postscan(). */ static void tasks_rcu_exit_srcu_stall(struct timer_list *unused); @@ -240,7 +240,6 @@ static const char *tasks_gp_state_getname(struct rcu_tasks *rtp) static void cblist_init_generic(struct rcu_tasks *rtp) { int cpu; - unsigned long flags; int lim; int shift; @@ -266,15 +265,15 @@ static void cblist_init_generic(struct rcu_tasks *rtp) WARN_ON_ONCE(!rtpcp); if (cpu) raw_spin_lock_init(&ACCESS_PRIVATE(rtpcp, lock)); - local_irq_save(flags); // serialize initialization if (rcu_segcblist_empty(&rtpcp->cblist)) rcu_segcblist_init(&rtpcp->cblist); - local_irq_restore(flags); INIT_WORK(&rtpcp->rtp_work, rcu_tasks_invoke_cbs_wq); rtpcp->cpu = cpu; rtpcp->rtpp = rtp; if (!rtpcp->rtp_blkd_tasks.next) INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks); + if (!rtpcp->rtp_exit_list.next) + INIT_LIST_HEAD(&rtpcp->rtp_exit_list); } pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name, @@ -851,10 +850,12 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) // number of voluntary context switches, and add that task to the // holdout list. // rcu_tasks_postscan(): -// Invoke synchronize_srcu() to ensure that all tasks that were -// in the process of exiting (and which thus might not know to -// synchronize with this RCU Tasks grace period) have completed -// exiting. +// Gather per-CPU lists of tasks in do_exit() to ensure that all +// tasks that were in the process of exiting (and which thus might +// not know to synchronize with this RCU Tasks grace period) have +// completed exiting. The synchronize_rcu() in rcu_tasks_postgp() +// will take care of any tasks stuck in the non-preemptible region +// of do_exit() following its call to exit_tasks_rcu_stop(). // check_all_holdout_tasks(), repeatedly until holdout list is empty: // Scans the holdout list, attempting to identify a quiescent state // for each task on the list. If there is a quiescent state, the @@ -867,8 +868,10 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) // with interrupts disabled. // // For each exiting task, the exit_tasks_rcu_start() and -// exit_tasks_rcu_finish() functions begin and end, respectively, the SRCU -// read-side critical sections waited for by rcu_tasks_postscan(). +// exit_tasks_rcu_finish() functions add and remove, respectively, the +// current task to a per-CPU list of tasks that rcu_tasks_postscan() must +// wait on. This is necessary because rcu_tasks_postscan() must wait on +// tasks that have already been removed from the global list of tasks. // // Pre-grace-period update-side code is ordered before the grace // via the raw_spin_lock.*rcu_node(). Pre-grace-period read-side code @@ -932,9 +935,13 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop) } } +void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func); +DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks"); + /* Processing between scanning taskslist and draining the holdout list. */ static void rcu_tasks_postscan(struct list_head *hop) { + int cpu; int rtsi = READ_ONCE(rcu_task_stall_info); if (!IS_ENABLED(CONFIG_TINY_RCU)) { @@ -948,9 +955,9 @@ static void rcu_tasks_postscan(struct list_head *hop) * this, divide the fragile exit path part in two intersecting * read side critical sections: * - * 1) An _SRCU_ read side starting before calling exit_notify(), - * which may remove the task from the tasklist, and ending after - * the final preempt_disable() call in do_exit(). + * 1) A task_struct list addition before calling exit_notify(), + * which may remove the task from the tasklist, with the + * removal after the final preempt_disable() call in do_exit(). * * 2) An _RCU_ read side starting with the final preempt_disable() * call in do_exit() and ending with the final call to schedule() @@ -959,7 +966,37 @@ static void rcu_tasks_postscan(struct list_head *hop) * This handles the part 1). And postgp will handle part 2) with a * call to synchronize_rcu(). */ - synchronize_srcu(&tasks_rcu_exit_srcu); + + for_each_possible_cpu(cpu) { + unsigned long j = jiffies + 1; + struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, cpu); + struct task_struct *t; + struct task_struct *t1; + struct list_head tmp; + + raw_spin_lock_irq_rcu_node(rtpcp); + list_for_each_entry_safe(t, t1, &rtpcp->rtp_exit_list, rcu_tasks_exit_list) { + if (list_empty(&t->rcu_tasks_holdout_list)) + rcu_tasks_pertask(t, hop); + + // RT kernels need frequent pauses, otherwise + // pause at least once per pair of jiffies. + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && time_before(jiffies, j)) + continue; + + // Keep our place in the list while pausing. + // Nothing else traverses this list, so adding a + // bare list_head is OK. + list_add(&tmp, &t->rcu_tasks_exit_list); + raw_spin_unlock_irq_rcu_node(rtpcp); + cond_resched(); // For CONFIG_PREEMPT=n kernels + raw_spin_lock_irq_rcu_node(rtpcp); + t1 = list_entry(tmp.next, struct task_struct, rcu_tasks_exit_list); + list_del(&tmp); + j = jiffies + 1; + } + raw_spin_unlock_irq_rcu_node(rtpcp); + } if (!IS_ENABLED(CONFIG_TINY_RCU)) del_timer_sync(&tasks_rcu_exit_srcu_stall_timer); @@ -1027,7 +1064,6 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp) * * In addition, this synchronize_rcu() waits for exiting tasks * to complete their final preempt_disable() region of execution, - * cleaning up after synchronize_srcu(&tasks_rcu_exit_srcu), * enforcing the whole region before tasklist removal until * the final schedule() with TASK_DEAD state to be an RCU TASKS * read side critical section. @@ -1035,9 +1071,6 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp) synchronize_rcu(); } -void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func); -DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks"); - static void tasks_rcu_exit_srcu_stall(struct timer_list *unused) { #ifndef CONFIG_TINY_RCU @@ -1118,7 +1151,6 @@ module_param(rcu_tasks_lazy_ms, int, 0444); static int __init rcu_spawn_tasks_kthread(void) { - cblist_init_generic(&rcu_tasks); rcu_tasks.gp_sleep = HZ / 10; rcu_tasks.init_fract = HZ / 10; if (rcu_tasks_lazy_ms >= 0) @@ -1147,25 +1179,48 @@ struct task_struct *get_rcu_tasks_gp_kthread(void) EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread); /* - * Contribute to protect against tasklist scan blind spot while the - * task is exiting and may be removed from the tasklist. See - * corresponding synchronize_srcu() for further details. + * Protect against tasklist scan blind spot while the task is exiting and + * may be removed from the tasklist. Do this by adding the task to yet + * another list. + * + * Note that the task will remove itself from this list, so there is no + * need for get_task_struct(), except in the case where rcu_tasks_pertask() + * adds it to the holdout list, in which case rcu_tasks_pertask() supplies + * the needed get_task_struct(). */ -void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) +void exit_tasks_rcu_start(void) { - current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu); + unsigned long flags; + struct rcu_tasks_percpu *rtpcp; + struct task_struct *t = current; + + WARN_ON_ONCE(!list_empty(&t->rcu_tasks_exit_list)); + preempt_disable(); + rtpcp = this_cpu_ptr(rcu_tasks.rtpcpu); + t->rcu_tasks_exit_cpu = smp_processor_id(); + raw_spin_lock_irqsave_rcu_node(rtpcp, flags); + if (!rtpcp->rtp_exit_list.next) + INIT_LIST_HEAD(&rtpcp->rtp_exit_list); + list_add(&t->rcu_tasks_exit_list, &rtpcp->rtp_exit_list); + raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); + preempt_enable(); } /* - * Contribute to protect against tasklist scan blind spot while the - * task is exiting and may be removed from the tasklist. See - * corresponding synchronize_srcu() for further details. + * Remove the task from the "yet another list" because do_exit() is now + * non-preemptible, allowing synchronize_rcu() to wait beyond this point. */ -void exit_tasks_rcu_stop(void) __releases(&tasks_rcu_exit_srcu) +void exit_tasks_rcu_stop(void) { + unsigned long flags; + struct rcu_tasks_percpu *rtpcp; struct task_struct *t = current; - __srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx); + WARN_ON_ONCE(list_empty(&t->rcu_tasks_exit_list)); + rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, t->rcu_tasks_exit_cpu); + raw_spin_lock_irqsave_rcu_node(rtpcp, flags); + list_del_init(&t->rcu_tasks_exit_list); + raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); } /* @@ -1282,7 +1337,6 @@ module_param(rcu_tasks_rude_lazy_ms, int, 0444); static int __init rcu_spawn_tasks_rude_kthread(void) { - cblist_init_generic(&rcu_tasks_rude); rcu_tasks_rude.gp_sleep = HZ / 10; if (rcu_tasks_rude_lazy_ms >= 0) rcu_tasks_rude.lazy_jiffies = msecs_to_jiffies(rcu_tasks_rude_lazy_ms); @@ -1914,7 +1968,6 @@ module_param(rcu_tasks_trace_lazy_ms, int, 0444); static int __init rcu_spawn_tasks_trace_kthread(void) { - cblist_init_generic(&rcu_tasks_trace); if (IS_ENABLED(CONFIG_TASKS_TRACE_RCU_READ_MB)) { rcu_tasks_trace.gp_sleep = HZ / 10; rcu_tasks_trace.init_fract = HZ / 10; @@ -2086,6 +2139,24 @@ late_initcall(rcu_tasks_verify_schedule_work); static void rcu_tasks_initiate_self_tests(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ +void __init tasks_cblist_init_generic(void) +{ + lockdep_assert_irqs_disabled(); + WARN_ON(num_online_cpus() > 1); + +#ifdef CONFIG_TASKS_RCU + cblist_init_generic(&rcu_tasks); +#endif + +#ifdef CONFIG_TASKS_RUDE_RCU + cblist_init_generic(&rcu_tasks_rude); +#endif + +#ifdef CONFIG_TASKS_TRACE_RCU + cblist_init_generic(&rcu_tasks_trace); +#endif +} + void __init rcu_init_tasks_generic(void) { #ifdef CONFIG_TASKS_RCU diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c index fec804b79080..705c0d16850a 100644 --- a/kernel/rcu/tiny.c +++ b/kernel/rcu/tiny.c @@ -261,4 +261,5 @@ void __init rcu_init(void) { open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); rcu_early_boot_tests(); + tasks_cblist_init_generic(); } diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index b2bccfd37c38..d9642dd06c25 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -145,7 +145,7 @@ static int rcu_scheduler_fully_active __read_mostly; static void rcu_report_qs_rnp(unsigned long mask, struct rcu_node *rnp, unsigned long gps, unsigned long flags); -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu); +static struct task_struct *rcu_boost_task(struct rcu_node *rnp); static void invoke_rcu_core(void); static void rcu_report_exp_rdp(struct rcu_data *rdp); static void sync_sched_exp_online_cleanup(int cpu); @@ -2145,6 +2145,12 @@ static void rcu_do_batch(struct rcu_data *rdp) * Extract the list of ready callbacks, disabling IRQs to prevent * races with call_rcu() from interrupt handlers. Leave the * callback counts, as rcu_barrier() needs to be conservative. + * + * Callbacks execution is fully ordered against preceding grace period + * completion (materialized by rnp->gp_seq update) thanks to the + * smp_mb__after_unlock_lock() upon node locking required for callbacks + * advancing. In NOCB mode this ordering is then further relayed through + * the nocb locking that protects both callbacks advancing and extraction. */ rcu_nocb_lock_irqsave(rdp, flags); WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); @@ -2591,12 +2597,26 @@ static int __init rcu_spawn_core_kthreads(void) return 0; } +static void rcutree_enqueue(struct rcu_data *rdp, struct rcu_head *head, rcu_callback_t func) +{ + rcu_segcblist_enqueue(&rdp->cblist, head); + if (__is_kvfree_rcu_offset((unsigned long)func)) + trace_rcu_kvfree_callback(rcu_state.name, head, + (unsigned long)func, + rcu_segcblist_n_cbs(&rdp->cblist)); + else + trace_rcu_callback(rcu_state.name, head, + rcu_segcblist_n_cbs(&rdp->cblist)); + trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued")); +} + /* * Handle any core-RCU processing required by a call_rcu() invocation. */ -static void __call_rcu_core(struct rcu_data *rdp, struct rcu_head *head, - unsigned long flags) +static void call_rcu_core(struct rcu_data *rdp, struct rcu_head *head, + rcu_callback_t func, unsigned long flags) { + rcutree_enqueue(rdp, head, func); /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. @@ -2692,7 +2712,6 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in) unsigned long flags; bool lazy; struct rcu_data *rdp; - bool was_alldone; /* Misaligned rcu_head! */ WARN_ON_ONCE((unsigned long)head & (sizeof(void *) - 1)); @@ -2729,30 +2748,18 @@ __call_rcu_common(struct rcu_head *head, rcu_callback_t func, bool lazy_in) } check_cb_ovld(rdp); - if (rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy)) - return; // Enqueued onto ->nocb_bypass, so just leave. - // If no-CBs CPU gets here, rcu_nocb_try_bypass() acquired ->nocb_lock. - rcu_segcblist_enqueue(&rdp->cblist, head); - if (__is_kvfree_rcu_offset((unsigned long)func)) - trace_rcu_kvfree_callback(rcu_state.name, head, - (unsigned long)func, - rcu_segcblist_n_cbs(&rdp->cblist)); - else - trace_rcu_callback(rcu_state.name, head, - rcu_segcblist_n_cbs(&rdp->cblist)); - trace_rcu_segcb_stats(&rdp->cblist, TPS("SegCBQueued")); - - /* Go handle any RCU core processing required. */ - if (unlikely(rcu_rdp_is_offloaded(rdp))) { - __call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */ - } else { - __call_rcu_core(rdp, head, flags); - local_irq_restore(flags); - } + if (unlikely(rcu_rdp_is_offloaded(rdp))) + call_rcu_nocb(rdp, head, func, flags, lazy); + else + call_rcu_core(rdp, head, func, flags); + local_irq_restore(flags); } #ifdef CONFIG_RCU_LAZY +static bool enable_rcu_lazy __read_mostly = !IS_ENABLED(CONFIG_RCU_LAZY_DEFAULT_OFF); +module_param(enable_rcu_lazy, bool, 0444); + /** * call_rcu_hurry() - Queue RCU callback for invocation after grace period, and * flush all lazy callbacks (including the new one) to the main ->cblist while @@ -2778,6 +2785,8 @@ void call_rcu_hurry(struct rcu_head *head, rcu_callback_t func) __call_rcu_common(head, func, false); } EXPORT_SYMBOL_GPL(call_rcu_hurry); +#else +#define enable_rcu_lazy false #endif /** @@ -2826,7 +2835,7 @@ EXPORT_SYMBOL_GPL(call_rcu_hurry); */ void call_rcu(struct rcu_head *head, rcu_callback_t func) { - __call_rcu_common(head, func, IS_ENABLED(CONFIG_RCU_LAZY)); + __call_rcu_common(head, func, enable_rcu_lazy); } EXPORT_SYMBOL_GPL(call_rcu); @@ -4394,6 +4403,66 @@ rcu_boot_init_percpu_data(int cpu) rcu_boot_init_nocb_percpu_data(rdp); } +struct kthread_worker *rcu_exp_gp_kworker; + +static void rcu_spawn_exp_par_gp_kworker(struct rcu_node *rnp) +{ + struct kthread_worker *kworker; + const char *name = "rcu_exp_par_gp_kthread_worker/%d"; + struct sched_param param = { .sched_priority = kthread_prio }; + int rnp_index = rnp - rcu_get_root(); + + if (rnp->exp_kworker) + return; + + kworker = kthread_create_worker(0, name, rnp_index); + if (IS_ERR_OR_NULL(kworker)) { + pr_err("Failed to create par gp kworker on %d/%d\n", + rnp->grplo, rnp->grphi); + return; + } + WRITE_ONCE(rnp->exp_kworker, kworker); + + if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD)) + sched_setscheduler_nocheck(kworker->task, SCHED_FIFO, ¶m); +} + +static struct task_struct *rcu_exp_par_gp_task(struct rcu_node *rnp) +{ + struct kthread_worker *kworker = READ_ONCE(rnp->exp_kworker); + + if (!kworker) + return NULL; + + return kworker->task; +} + +static void __init rcu_start_exp_gp_kworker(void) +{ + const char *name = "rcu_exp_gp_kthread_worker"; + struct sched_param param = { .sched_priority = kthread_prio }; + + rcu_exp_gp_kworker = kthread_create_worker(0, name); + if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { + pr_err("Failed to create %s!\n", name); + rcu_exp_gp_kworker = NULL; + return; + } + + if (IS_ENABLED(CONFIG_RCU_EXP_KTHREAD)) + sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, ¶m); +} + +static void rcu_spawn_rnp_kthreads(struct rcu_node *rnp) +{ + if (rcu_scheduler_fully_active) { + mutex_lock(&rnp->kthread_mutex); + rcu_spawn_one_boost_kthread(rnp); + rcu_spawn_exp_par_gp_kworker(rnp); + mutex_unlock(&rnp->kthread_mutex); + } +} + /* * Invoked early in the CPU-online process, when pretty much all services * are available. The incoming CPU is not present. @@ -4442,7 +4511,7 @@ int rcutree_prepare_cpu(unsigned int cpu) rdp->rcu_iw_gp_seq = rdp->gp_seq - 1; trace_rcu_grace_period(rcu_state.name, rdp->gp_seq, TPS("cpuonl")); raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - rcu_spawn_one_boost_kthread(rnp); + rcu_spawn_rnp_kthreads(rnp); rcu_spawn_cpu_nocb_kthread(cpu); WRITE_ONCE(rcu_state.n_online_cpus, rcu_state.n_online_cpus + 1); @@ -4450,13 +4519,64 @@ int rcutree_prepare_cpu(unsigned int cpu) } /* - * Update RCU priority boot kthread affinity for CPU-hotplug changes. + * Update kthreads affinity during CPU-hotplug changes. + * + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still + * held, so the value of rnp->qsmaskinit will be stable. + * + * We don't include outgoingcpu in the affinity set, use -1 if there is + * no outgoing CPU. If there are no CPUs left in the affinity set, + * this function allows the kthread to execute on any CPU. + * + * Any future concurrent calls are serialized via ->kthread_mutex. */ -static void rcutree_affinity_setting(unsigned int cpu, int outgoing) +static void rcutree_affinity_setting(unsigned int cpu, int outgoingcpu) { - struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu); + cpumask_var_t cm; + unsigned long mask; + struct rcu_data *rdp; + struct rcu_node *rnp; + struct task_struct *task_boost, *task_exp; + + rdp = per_cpu_ptr(&rcu_data, cpu); + rnp = rdp->mynode; + + task_boost = rcu_boost_task(rnp); + task_exp = rcu_exp_par_gp_task(rnp); + + /* + * If CPU is the boot one, those tasks are created later from early + * initcall since kthreadd must be created first. + */ + if (!task_boost && !task_exp) + return; + + if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) + return; + + mutex_lock(&rnp->kthread_mutex); + mask = rcu_rnp_online_cpus(rnp); + for_each_leaf_node_possible_cpu(rnp, cpu) + if ((mask & leaf_node_cpu_bit(rnp, cpu)) && + cpu != outgoingcpu) + cpumask_set_cpu(cpu, cm); + cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU)); + if (cpumask_empty(cm)) { + cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU)); + if (outgoingcpu >= 0) + cpumask_clear_cpu(outgoingcpu, cm); + } + + if (task_exp) + set_cpus_allowed_ptr(task_exp, cm); + + if (task_boost) + set_cpus_allowed_ptr(task_boost, cm); - rcu_boost_kthread_setaffinity(rdp->mynode, outgoing); + mutex_unlock(&rnp->kthread_mutex); + + free_cpumask_var(cm); } /* @@ -4640,8 +4760,9 @@ void rcutree_migrate_callbacks(int cpu) __call_rcu_nocb_wake(my_rdp, true, flags); } else { rcu_nocb_unlock(my_rdp); /* irqs remain disabled. */ - raw_spin_unlock_irqrestore_rcu_node(my_rnp, flags); + raw_spin_unlock_rcu_node(my_rnp); /* irqs remain disabled. */ } + local_irq_restore(flags); if (needwake) rcu_gp_kthread_wake(); lockdep_assert_irqs_enabled(); @@ -4730,51 +4851,6 @@ static int rcu_pm_notify(struct notifier_block *self, return NOTIFY_OK; } -#ifdef CONFIG_RCU_EXP_KTHREAD -struct kthread_worker *rcu_exp_gp_kworker; -struct kthread_worker *rcu_exp_par_gp_kworker; - -static void __init rcu_start_exp_gp_kworkers(void) -{ - const char *par_gp_kworker_name = "rcu_exp_par_gp_kthread_worker"; - const char *gp_kworker_name = "rcu_exp_gp_kthread_worker"; - struct sched_param param = { .sched_priority = kthread_prio }; - - rcu_exp_gp_kworker = kthread_create_worker(0, gp_kworker_name); - if (IS_ERR_OR_NULL(rcu_exp_gp_kworker)) { - pr_err("Failed to create %s!\n", gp_kworker_name); - return; - } - - rcu_exp_par_gp_kworker = kthread_create_worker(0, par_gp_kworker_name); - if (IS_ERR_OR_NULL(rcu_exp_par_gp_kworker)) { - pr_err("Failed to create %s!\n", par_gp_kworker_name); - kthread_destroy_worker(rcu_exp_gp_kworker); - return; - } - - sched_setscheduler_nocheck(rcu_exp_gp_kworker->task, SCHED_FIFO, ¶m); - sched_setscheduler_nocheck(rcu_exp_par_gp_kworker->task, SCHED_FIFO, - ¶m); -} - -static inline void rcu_alloc_par_gp_wq(void) -{ -} -#else /* !CONFIG_RCU_EXP_KTHREAD */ -struct workqueue_struct *rcu_par_gp_wq; - -static void __init rcu_start_exp_gp_kworkers(void) -{ -} - -static inline void rcu_alloc_par_gp_wq(void) -{ - rcu_par_gp_wq = alloc_workqueue("rcu_par_gp", WQ_MEM_RECLAIM, 0); - WARN_ON(!rcu_par_gp_wq); -} -#endif /* CONFIG_RCU_EXP_KTHREAD */ - /* * Spawn the kthreads that handle RCU's grace periods. */ @@ -4809,10 +4885,10 @@ static int __init rcu_spawn_gp_kthread(void) * due to rcu_scheduler_fully_active. */ rcu_spawn_cpu_nocb_kthread(smp_processor_id()); - rcu_spawn_one_boost_kthread(rdp->mynode); + rcu_spawn_rnp_kthreads(rdp->mynode); rcu_spawn_core_kthreads(); /* Create kthread worker for expedited GPs */ - rcu_start_exp_gp_kworkers(); + rcu_start_exp_gp_kworker(); return 0; } early_initcall(rcu_spawn_gp_kthread); @@ -4915,7 +4991,7 @@ static void __init rcu_init_one(void) init_waitqueue_head(&rnp->exp_wq[2]); init_waitqueue_head(&rnp->exp_wq[3]); spin_lock_init(&rnp->exp_lock); - mutex_init(&rnp->boost_kthread_mutex); + mutex_init(&rnp->kthread_mutex); raw_spin_lock_init(&rnp->exp_poll_lock); rnp->exp_seq_poll_rq = RCU_GET_STATE_COMPLETED; INIT_WORK(&rnp->exp_poll_wq, sync_rcu_do_polled_gp); @@ -5152,7 +5228,6 @@ void __init rcu_init(void) /* Create workqueue for Tree SRCU and for expedited GPs. */ rcu_gp_wq = alloc_workqueue("rcu_gp", WQ_MEM_RECLAIM, 0); WARN_ON(!rcu_gp_wq); - rcu_alloc_par_gp_wq(); /* Fill in default value for rcutree.qovld boot parameter. */ /* -After- the rcu_node ->lock fields are initialized! */ @@ -5165,6 +5240,8 @@ void __init rcu_init(void) (void)start_poll_synchronize_rcu_expedited(); rcu_test_sync_prims(); + + tasks_cblist_init_generic(); } #include "tree_stall.h" diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h index e9821a8422db..df48160b3136 100644 --- a/kernel/rcu/tree.h +++ b/kernel/rcu/tree.h @@ -21,14 +21,10 @@ #include "rcu_segcblist.h" -/* Communicate arguments to a workqueue handler. */ +/* Communicate arguments to a kthread worker handler. */ struct rcu_exp_work { unsigned long rew_s; -#ifdef CONFIG_RCU_EXP_KTHREAD struct kthread_work rew_work; -#else - struct work_struct rew_work; -#endif /* CONFIG_RCU_EXP_KTHREAD */ }; /* RCU's kthread states for tracing. */ @@ -72,6 +68,9 @@ struct rcu_node { /* Online CPUs for next expedited GP. */ /* Any CPU that has ever been online will */ /* have its bit set. */ + struct kthread_worker *exp_kworker; + /* Workers performing per node expedited GP */ + /* initialization. */ unsigned long cbovldmask; /* CPUs experiencing callback overload. */ unsigned long ffmask; /* Fully functional CPUs. */ @@ -113,7 +112,7 @@ struct rcu_node { /* side effect, not as a lock. */ unsigned long boost_time; /* When to start boosting (jiffies). */ - struct mutex boost_kthread_mutex; + struct mutex kthread_mutex; /* Exclusion for thread spawning and affinity */ /* manipulation. */ struct task_struct *boost_kthread_task; @@ -467,11 +466,10 @@ static void rcu_init_one_nocb(struct rcu_node *rnp); static bool wake_nocb_gp(struct rcu_data *rdp, bool force); static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, unsigned long j, bool lazy); -static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - bool *was_alldone, unsigned long flags, - bool lazy); -static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty, - unsigned long flags); +static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head, + rcu_callback_t func, unsigned long flags, bool lazy); +static void __maybe_unused __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty, + unsigned long flags); static int rcu_nocb_need_deferred_wakeup(struct rcu_data *rdp, int level); static bool do_nocb_deferred_wakeup(struct rcu_data *rdp); static void rcu_boot_init_nocb_percpu_data(struct rcu_data *rdp); diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h index 2ac440bc7e10..6b83537480b1 100644 --- a/kernel/rcu/tree_exp.h +++ b/kernel/rcu/tree_exp.h @@ -198,10 +198,9 @@ static void __rcu_report_exp_rnp(struct rcu_node *rnp, } if (rnp->parent == NULL) { raw_spin_unlock_irqrestore_rcu_node(rnp, flags); - if (wake) { - smp_mb(); /* EGP done before wake_up(). */ + if (wake) swake_up_one_online(&rcu_state.expedited_wq); - } + break; } mask = rnp->grpmask; @@ -419,7 +418,6 @@ retry_ipi: static void rcu_exp_sel_wait_wake(unsigned long s); -#ifdef CONFIG_RCU_EXP_KTHREAD static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp) { struct rcu_exp_work *rewp = @@ -428,9 +426,14 @@ static void sync_rcu_exp_select_node_cpus(struct kthread_work *wp) __sync_rcu_exp_select_node_cpus(rewp); } -static inline bool rcu_gp_par_worker_started(void) +static inline bool rcu_exp_worker_started(void) +{ + return !!READ_ONCE(rcu_exp_gp_kworker); +} + +static inline bool rcu_exp_par_worker_started(struct rcu_node *rnp) { - return !!READ_ONCE(rcu_exp_par_gp_kworker); + return !!READ_ONCE(rnp->exp_kworker); } static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp) @@ -441,7 +444,7 @@ static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp) * another work item on the same kthread worker can result in * deadlock. */ - kthread_queue_work(rcu_exp_par_gp_kworker, &rnp->rew.rew_work); + kthread_queue_work(READ_ONCE(rnp->exp_kworker), &rnp->rew.rew_work); } static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp) @@ -466,64 +469,6 @@ static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew kthread_queue_work(rcu_exp_gp_kworker, &rew->rew_work); } -static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew) -{ -} -#else /* !CONFIG_RCU_EXP_KTHREAD */ -static void sync_rcu_exp_select_node_cpus(struct work_struct *wp) -{ - struct rcu_exp_work *rewp = - container_of(wp, struct rcu_exp_work, rew_work); - - __sync_rcu_exp_select_node_cpus(rewp); -} - -static inline bool rcu_gp_par_worker_started(void) -{ - return !!READ_ONCE(rcu_par_gp_wq); -} - -static inline void sync_rcu_exp_select_cpus_queue_work(struct rcu_node *rnp) -{ - int cpu = find_next_bit(&rnp->ffmask, BITS_PER_LONG, -1); - - INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus); - /* If all offline, queue the work on an unbound CPU. */ - if (unlikely(cpu > rnp->grphi - rnp->grplo)) - cpu = WORK_CPU_UNBOUND; - else - cpu += rnp->grplo; - queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work); -} - -static inline void sync_rcu_exp_select_cpus_flush_work(struct rcu_node *rnp) -{ - flush_work(&rnp->rew.rew_work); -} - -/* - * Work-queue handler to drive an expedited grace period forward. - */ -static void wait_rcu_exp_gp(struct work_struct *wp) -{ - struct rcu_exp_work *rewp; - - rewp = container_of(wp, struct rcu_exp_work, rew_work); - rcu_exp_sel_wait_wake(rewp->rew_s); -} - -static inline void synchronize_rcu_expedited_queue_work(struct rcu_exp_work *rew) -{ - INIT_WORK_ONSTACK(&rew->rew_work, wait_rcu_exp_gp); - queue_work(rcu_gp_wq, &rew->rew_work); -} - -static inline void synchronize_rcu_expedited_destroy_work(struct rcu_exp_work *rew) -{ - destroy_work_on_stack(&rew->rew_work); -} -#endif /* CONFIG_RCU_EXP_KTHREAD */ - /* * Select the nodes that the upcoming expedited grace period needs * to wait for. @@ -541,7 +486,7 @@ static void sync_rcu_exp_select_cpus(void) rnp->exp_need_flush = false; if (!READ_ONCE(rnp->expmask)) continue; /* Avoid early boot non-existent wq. */ - if (!rcu_gp_par_worker_started() || + if (!rcu_exp_par_worker_started(rnp) || rcu_scheduler_active != RCU_SCHEDULER_RUNNING || rcu_is_last_leaf_node(rnp)) { /* No worker started yet or last leaf, do direct call. */ @@ -956,7 +901,6 @@ static void rcu_exp_print_detail_task_stall_rnp(struct rcu_node *rnp) */ void synchronize_rcu_expedited(void) { - bool boottime = (rcu_scheduler_active == RCU_SCHEDULER_INIT); unsigned long flags; struct rcu_exp_work rew; struct rcu_node *rnp; @@ -996,7 +940,7 @@ void synchronize_rcu_expedited(void) return; /* Someone else did our work for us. */ /* Ensure that load happens before action based on it. */ - if (unlikely(boottime)) { + if (unlikely((rcu_scheduler_active == RCU_SCHEDULER_INIT) || !rcu_exp_worker_started())) { /* Direct call during scheduler init and early_initcalls(). */ rcu_exp_sel_wait_wake(s); } else { @@ -1013,9 +957,6 @@ void synchronize_rcu_expedited(void) /* Let the next expedited grace period start. */ mutex_unlock(&rcu_state.exp_mutex); - - if (likely(!boottime)) - synchronize_rcu_expedited_destroy_work(&rew); } EXPORT_SYMBOL_GPL(synchronize_rcu_expedited); diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h index 4efbf7333d4e..3f85577bddd4 100644 --- a/kernel/rcu/tree_nocb.h +++ b/kernel/rcu/tree_nocb.h @@ -256,6 +256,7 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force) return __wake_nocb_gp(rdp_gp, rdp, force, flags); } +#ifdef CONFIG_RCU_LAZY /* * LAZY_FLUSH_JIFFIES decides the maximum amount of time that * can elapse before lazy callbacks are flushed. Lazy callbacks @@ -264,21 +265,20 @@ static bool wake_nocb_gp(struct rcu_data *rdp, bool force) * left unsubmitted to RCU after those many jiffies. */ #define LAZY_FLUSH_JIFFIES (10 * HZ) -static unsigned long jiffies_till_flush = LAZY_FLUSH_JIFFIES; +static unsigned long jiffies_lazy_flush = LAZY_FLUSH_JIFFIES; -#ifdef CONFIG_RCU_LAZY // To be called only from test code. -void rcu_lazy_set_jiffies_till_flush(unsigned long jif) +void rcu_set_jiffies_lazy_flush(unsigned long jif) { - jiffies_till_flush = jif; + jiffies_lazy_flush = jif; } -EXPORT_SYMBOL(rcu_lazy_set_jiffies_till_flush); +EXPORT_SYMBOL(rcu_set_jiffies_lazy_flush); -unsigned long rcu_lazy_get_jiffies_till_flush(void) +unsigned long rcu_get_jiffies_lazy_flush(void) { - return jiffies_till_flush; + return jiffies_lazy_flush; } -EXPORT_SYMBOL(rcu_lazy_get_jiffies_till_flush); +EXPORT_SYMBOL(rcu_get_jiffies_lazy_flush); #endif /* @@ -299,7 +299,7 @@ static void wake_nocb_gp_defer(struct rcu_data *rdp, int waketype, */ if (waketype == RCU_NOCB_WAKE_LAZY && rdp->nocb_defer_wakeup == RCU_NOCB_WAKE_NOT) { - mod_timer(&rdp_gp->nocb_timer, jiffies + jiffies_till_flush); + mod_timer(&rdp_gp->nocb_timer, jiffies + rcu_get_jiffies_lazy_flush()); WRITE_ONCE(rdp_gp->nocb_defer_wakeup, waketype); } else if (waketype == RCU_NOCB_WAKE_BYPASS) { mod_timer(&rdp_gp->nocb_timer, jiffies + 2); @@ -482,7 +482,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, // flush ->nocb_bypass to ->cblist. if ((ncbs && !bypass_is_lazy && j != READ_ONCE(rdp->nocb_bypass_first)) || (ncbs && bypass_is_lazy && - (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush))) || + (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + rcu_get_jiffies_lazy_flush()))) || ncbs >= qhimark) { rcu_nocb_lock(rdp); *was_alldone = !rcu_segcblist_pend_cbs(&rdp->cblist); @@ -532,9 +532,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, // 2. Both of these conditions are met: // a. The bypass list previously had only lazy CBs, and: // b. The new CB is non-lazy. - if (ncbs && (!bypass_is_lazy || lazy)) { - local_irq_restore(flags); - } else { + if (!ncbs || (bypass_is_lazy && !lazy)) { // No-CBs GP kthread might be indefinitely asleep, if so, wake. rcu_nocb_lock(rdp); // Rare during call_rcu() flood. if (!rcu_segcblist_pend_cbs(&rdp->cblist)) { @@ -544,7 +542,7 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, } else { trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("FirstBQnoWake")); - rcu_nocb_unlock_irqrestore(rdp, flags); + rcu_nocb_unlock(rdp); } } return true; // Callback already enqueued. @@ -566,11 +564,12 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, long lazy_len; long len; struct task_struct *t; + struct rcu_data *rdp_gp = rdp->nocb_gp_rdp; // If we are being polled or there is no kthread, just leave. t = READ_ONCE(rdp->nocb_gp_kthread); if (rcu_nocb_poll || !t) { - rcu_nocb_unlock_irqrestore(rdp, flags); + rcu_nocb_unlock(rdp); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNotPoll")); return; @@ -583,17 +582,17 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, rdp->qlen_last_fqs_check = len; // Only lazy CBs in bypass list if (lazy_len && bypass_len == lazy_len) { - rcu_nocb_unlock_irqrestore(rdp, flags); + rcu_nocb_unlock(rdp); wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_LAZY, TPS("WakeLazy")); } else if (!irqs_disabled_flags(flags)) { /* ... if queue was empty ... */ - rcu_nocb_unlock_irqrestore(rdp, flags); + rcu_nocb_unlock(rdp); wake_nocb_gp(rdp, false); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeEmpty")); } else { - rcu_nocb_unlock_irqrestore(rdp, flags); + rcu_nocb_unlock(rdp); wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE, TPS("WakeEmptyIsDeferred")); } @@ -610,20 +609,32 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone, smp_mb(); /* Enqueue before timer_pending(). */ if ((rdp->nocb_cb_sleep || !rcu_segcblist_ready_cbs(&rdp->cblist)) && - !timer_pending(&rdp->nocb_timer)) { - rcu_nocb_unlock_irqrestore(rdp, flags); + !timer_pending(&rdp_gp->nocb_timer)) { + rcu_nocb_unlock(rdp); wake_nocb_gp_defer(rdp, RCU_NOCB_WAKE_FORCE, TPS("WakeOvfIsDeferred")); } else { - rcu_nocb_unlock_irqrestore(rdp, flags); + rcu_nocb_unlock(rdp); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot")); } } else { - rcu_nocb_unlock_irqrestore(rdp, flags); + rcu_nocb_unlock(rdp); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WakeNot")); } } +static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head, + rcu_callback_t func, unsigned long flags, bool lazy) +{ + bool was_alldone; + + if (!rcu_nocb_try_bypass(rdp, head, &was_alldone, flags, lazy)) { + /* Not enqueued on bypass but locked, do regular enqueue */ + rcutree_enqueue(rdp, head, func); + __call_rcu_nocb_wake(rdp, was_alldone, flags); /* unlocks */ + } +} + static int nocb_gp_toggle_rdp(struct rcu_data *rdp, bool *wake_state) { @@ -723,7 +734,7 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) lazy_ncbs = READ_ONCE(rdp->lazy_len); if (bypass_ncbs && (lazy_ncbs == bypass_ncbs) && - (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + jiffies_till_flush) || + (time_after(j, READ_ONCE(rdp->nocb_bypass_first) + rcu_get_jiffies_lazy_flush()) || bypass_ncbs > 2 * qhimark)) { flush_bypass = true; } else if (bypass_ncbs && (lazy_ncbs != bypass_ncbs) && @@ -779,7 +790,6 @@ static void nocb_gp_wait(struct rcu_data *my_rdp) if (rcu_segcblist_ready_cbs(&rdp->cblist)) { needwake = rdp->nocb_cb_sleep; WRITE_ONCE(rdp->nocb_cb_sleep, false); - smp_mb(); /* CB invocation -after- GP end. */ } else { needwake = false; } @@ -933,8 +943,7 @@ static void nocb_cb_wait(struct rcu_data *rdp) swait_event_interruptible_exclusive(rdp->nocb_cb_wq, nocb_cb_wait_cond(rdp)); - // VVV Ensure CB invocation follows _sleep test. - if (smp_load_acquire(&rdp->nocb_cb_sleep)) { // ^^^ + if (READ_ONCE(rdp->nocb_cb_sleep)) { WARN_ON(signal_pending(current)); trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("WokeEmpty")); } @@ -1383,7 +1392,7 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc) rcu_nocb_unlock_irqrestore(rdp, flags); continue; } - WARN_ON_ONCE(!rcu_nocb_flush_bypass(rdp, NULL, jiffies, false)); + rcu_nocb_try_flush_bypass(rdp, jiffies); rcu_nocb_unlock_irqrestore(rdp, flags); wake_nocb_gp(rdp, false); sc->nr_to_scan -= _count; @@ -1768,10 +1777,10 @@ static bool rcu_nocb_flush_bypass(struct rcu_data *rdp, struct rcu_head *rhp, return true; } -static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp, - bool *was_alldone, unsigned long flags, bool lazy) +static void call_rcu_nocb(struct rcu_data *rdp, struct rcu_head *head, + rcu_callback_t func, unsigned long flags, bool lazy) { - return false; + WARN_ON_ONCE(1); /* Should be dead code! */ } static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_empty, diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h index 41021080ad25..36a8b5dbf5b5 100644 --- a/kernel/rcu/tree_plugin.h +++ b/kernel/rcu/tree_plugin.h @@ -1195,14 +1195,13 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) struct sched_param sp; struct task_struct *t; - mutex_lock(&rnp->boost_kthread_mutex); - if (rnp->boost_kthread_task || !rcu_scheduler_fully_active) - goto out; + if (rnp->boost_kthread_task) + return; t = kthread_create(rcu_boost_kthread, (void *)rnp, "rcub/%d", rnp_index); if (WARN_ON_ONCE(IS_ERR(t))) - goto out; + return; raw_spin_lock_irqsave_rcu_node(rnp, flags); rnp->boost_kthread_task = t; @@ -1210,48 +1209,11 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) sp.sched_priority = kthread_prio; sched_setscheduler_nocheck(t, SCHED_FIFO, &sp); wake_up_process(t); /* get to TASK_INTERRUPTIBLE quickly. */ - - out: - mutex_unlock(&rnp->boost_kthread_mutex); } -/* - * Set the per-rcu_node kthread's affinity to cover all CPUs that are - * served by the rcu_node in question. The CPU hotplug lock is still - * held, so the value of rnp->qsmaskinit will be stable. - * - * We don't include outgoingcpu in the affinity set, use -1 if there is - * no outgoing CPU. If there are no CPUs left in the affinity set, - * this function allows the kthread to execute on any CPU. - * - * Any future concurrent calls are serialized via ->boost_kthread_mutex. - */ -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +static struct task_struct *rcu_boost_task(struct rcu_node *rnp) { - struct task_struct *t = rnp->boost_kthread_task; - unsigned long mask; - cpumask_var_t cm; - int cpu; - - if (!t) - return; - if (!zalloc_cpumask_var(&cm, GFP_KERNEL)) - return; - mutex_lock(&rnp->boost_kthread_mutex); - mask = rcu_rnp_online_cpus(rnp); - for_each_leaf_node_possible_cpu(rnp, cpu) - if ((mask & leaf_node_cpu_bit(rnp, cpu)) && - cpu != outgoingcpu) - cpumask_set_cpu(cpu, cm); - cpumask_and(cm, cm, housekeeping_cpumask(HK_TYPE_RCU)); - if (cpumask_empty(cm)) { - cpumask_copy(cm, housekeeping_cpumask(HK_TYPE_RCU)); - if (outgoingcpu >= 0) - cpumask_clear_cpu(outgoingcpu, cm); - } - set_cpus_allowed_ptr(t, cm); - mutex_unlock(&rnp->boost_kthread_mutex); - free_cpumask_var(cm); + return READ_ONCE(rnp->boost_kthread_task); } #else /* #ifdef CONFIG_RCU_BOOST */ @@ -1270,10 +1232,10 @@ static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp) { } -static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu) +static struct task_struct *rcu_boost_task(struct rcu_node *rnp) { + return NULL; } - #endif /* #else #ifdef CONFIG_RCU_BOOST */ /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9116bcc90346..d44efa0d0611 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1792,7 +1792,6 @@ static void cpu_util_update_eff(struct cgroup_subsys_state *css); #endif #ifdef CONFIG_SYSCTL -#ifdef CONFIG_UCLAMP_TASK #ifdef CONFIG_UCLAMP_TASK_GROUP static void uclamp_update_root_tg(void) { @@ -1898,7 +1897,6 @@ undo: return result; } #endif -#endif static int uclamp_validate(struct task_struct *p, const struct sched_attr *attr) @@ -2065,7 +2063,7 @@ static void __init init_uclamp(void) } } -#else /* CONFIG_UCLAMP_TASK */ +#else /* !CONFIG_UCLAMP_TASK */ static inline void uclamp_rq_inc(struct rq *rq, struct task_struct *p) { } static inline void uclamp_rq_dec(struct rq *rq, struct task_struct *p) { } static inline int uclamp_validate(struct task_struct *p, @@ -3955,6 +3953,17 @@ void wake_up_if_idle(int cpu) } } +bool cpus_equal_capacity(int this_cpu, int that_cpu) +{ + if (!sched_asym_cpucap_active()) + return true; + + if (this_cpu == that_cpu) + return true; + + return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu); +} + bool cpus_share_cache(int this_cpu, int that_cpu) { if (this_cpu == that_cpu) @@ -6787,10 +6796,12 @@ static inline void sched_submit_work(struct task_struct *tsk) static void sched_update_worker(struct task_struct *tsk) { - if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { + if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) { + if (tsk->flags & PF_BLOCK_TS) + blk_plug_invalidate_ts(tsk); if (tsk->flags & PF_WQ_WORKER) wq_worker_running(tsk); - else + else if (tsk->flags & PF_IO_WORKER) io_wq_worker_running(tsk); } } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 533547e3c90a..03be0d1330a6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1831,6 +1831,12 @@ bool should_numa_migrate_memory(struct task_struct *p, struct folio *folio, int last_cpupid, this_cpupid; /* + * Cannot migrate to memoryless nodes. + */ + if (!node_state(dst_nid, N_MEMORY)) + return false; + + /* * The pages in slow memory node should be migrated according * to hot/cold instead of private/shared. */ @@ -7289,7 +7295,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu if (!available_idle_cpu(cpu)) { idle = false; if (*idle_cpu == -1) { - if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, p->cpus_ptr)) { + if (sched_idle_cpu(cpu) && cpumask_test_cpu(cpu, cpus)) { *idle_cpu = cpu; break; } @@ -7297,7 +7303,7 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu } break; } - if (*idle_cpu == -1 && cpumask_test_cpu(cpu, p->cpus_ptr)) + if (*idle_cpu == -1 && cpumask_test_cpu(cpu, cpus)) *idle_cpu = cpu; } @@ -7311,13 +7317,19 @@ static int select_idle_core(struct task_struct *p, int core, struct cpumask *cpu /* * Scan the local SMT mask for idle CPUs. */ -static int select_idle_smt(struct task_struct *p, int target) +static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { int cpu; for_each_cpu_and(cpu, cpu_smt_mask(target), p->cpus_ptr) { if (cpu == target) continue; + /* + * Check if the CPU is in the LLC scheduling domain of @target. + * Due to isolcpus, there is no guarantee that all the siblings are in the domain. + */ + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) + continue; if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) return cpu; } @@ -7341,7 +7353,7 @@ static inline int select_idle_core(struct task_struct *p, int core, struct cpuma return __select_idle_cpu(core, p); } -static inline int select_idle_smt(struct task_struct *p, int target) +static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { return -1; } @@ -7591,7 +7603,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) has_idle_core = test_idle_cores(target); if (!has_idle_core && cpus_share_cache(prev, target)) { - i = select_idle_smt(p, prev); + i = select_idle_smt(p, sd, prev); if ((unsigned int)i < nr_cpumask_bits) return i; } @@ -9237,19 +9249,17 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) static inline bool others_have_blocked(struct rq *rq) { - if (READ_ONCE(rq->avg_rt.util_avg)) + if (cpu_util_rt(rq)) return true; - if (READ_ONCE(rq->avg_dl.util_avg)) + if (cpu_util_dl(rq)) return true; if (thermal_load_avg(rq)) return true; -#ifdef CONFIG_HAVE_SCHED_AVG_IRQ - if (READ_ONCE(rq->avg_irq.util_avg)) + if (cpu_util_irq(rq)) return true; -#endif return false; } @@ -9506,8 +9516,8 @@ static unsigned long scale_rt_capacity(int cpu) * avg_thermal.load_avg tracks thermal pressure and the weighted * average uses the actual delta max capacity(load). */ - used = READ_ONCE(rq->avg_rt.util_avg); - used += READ_ONCE(rq->avg_dl.util_avg); + used = cpu_util_rt(rq); + used += cpu_util_dl(rq); used += thermal_load_avg(rq); if (unlikely(used >= max)) @@ -9740,51 +9750,49 @@ group_type group_classify(unsigned int imbalance_pct, */ static bool sched_use_asym_prio(struct sched_domain *sd, int cpu) { + if (!(sd->flags & SD_ASYM_PACKING)) + return false; + if (!sched_smt_active()) return true; return sd->flags & SD_SHARE_CPUCAPACITY || is_core_idle(cpu); } +static inline bool sched_asym(struct sched_domain *sd, int dst_cpu, int src_cpu) +{ + /* + * First check if @dst_cpu can do asym_packing load balance. Only do it + * if it has higher priority than @src_cpu. + */ + return sched_use_asym_prio(sd, dst_cpu) && + sched_asym_prefer(dst_cpu, src_cpu); +} + /** - * sched_asym - Check if the destination CPU can do asym_packing load balance + * sched_group_asym - Check if the destination CPU can do asym_packing balance * @env: The load balancing environment - * @sds: Load-balancing data with statistics of the local group * @sgs: Load-balancing statistics of the candidate busiest group * @group: The candidate busiest group * * @env::dst_cpu can do asym_packing if it has higher priority than the * preferred CPU of @group. * - * SMT is a special case. If we are balancing load between cores, @env::dst_cpu - * can do asym_packing balance only if all its SMT siblings are idle. Also, it - * can only do it if @group is an SMT group and has exactly on busy CPU. Larger - * imbalances in the number of CPUS are dealt with in find_busiest_group(). - * - * If we are balancing load within an SMT core, or at PKG domain level, always - * proceed. - * * Return: true if @env::dst_cpu can do with asym_packing load balance. False * otherwise. */ static inline bool -sched_asym(struct lb_env *env, struct sd_lb_stats *sds, struct sg_lb_stats *sgs, - struct sched_group *group) +sched_group_asym(struct lb_env *env, struct sg_lb_stats *sgs, struct sched_group *group) { - /* Ensure that the whole local core is idle, if applicable. */ - if (!sched_use_asym_prio(env->sd, env->dst_cpu)) - return false; - /* - * CPU priorities does not make sense for SMT cores with more than one + * CPU priorities do not make sense for SMT cores with more than one * busy sibling. */ - if (group->flags & SD_SHARE_CPUCAPACITY) { - if (sgs->group_weight - sgs->idle_cpus != 1) - return false; - } + if ((group->flags & SD_SHARE_CPUCAPACITY) && + (sgs->group_weight - sgs->idle_cpus != 1)) + return false; - return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu); + return sched_asym(env->sd, env->dst_cpu, group->asym_prefer_cpu); } /* One group has more than one SMT CPU while the other group does not */ @@ -9938,11 +9946,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_weight = group->group_weight; /* Check if dst CPU is idle and preferred to this group */ - if (!local_group && env->sd->flags & SD_ASYM_PACKING && - env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running && - sched_asym(env, sds, sgs, group)) { + if (!local_group && env->idle != CPU_NOT_IDLE && sgs->sum_h_nr_running && + sched_group_asym(env, sgs, group)) sgs->group_asym_packing = 1; - } /* Check for loaded SMT group to be balanced to dst CPU */ if (!local_group && smt_balance(env, sgs, group)) @@ -10006,9 +10012,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, switch (sgs->group_type) { case group_overloaded: /* Select the overloaded group with highest avg_load. */ - if (sgs->avg_load <= busiest->avg_load) - return false; - break; + return sgs->avg_load > busiest->avg_load; case group_imbalanced: /* @@ -10019,18 +10023,14 @@ static bool update_sd_pick_busiest(struct lb_env *env, case group_asym_packing: /* Prefer to move from lowest priority CPU's work */ - if (sched_asym_prefer(sg->asym_prefer_cpu, sds->busiest->asym_prefer_cpu)) - return false; - break; + return sched_asym_prefer(sds->busiest->asym_prefer_cpu, sg->asym_prefer_cpu); case group_misfit_task: /* * If we have more than one misfit sg go with the biggest * misfit. */ - if (sgs->group_misfit_task_load < busiest->group_misfit_task_load) - return false; - break; + return sgs->group_misfit_task_load > busiest->group_misfit_task_load; case group_smt_balance: /* @@ -10182,10 +10182,8 @@ static int idle_cpu_without(int cpu, struct task_struct *p) * be computed and tested before calling idle_cpu_without(). */ -#ifdef CONFIG_SMP if (rq->ttwu_pending) return 0; -#endif return 1; } @@ -10578,16 +10576,11 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd update_sg_lb_stats(env, sds, sg, sgs, &sg_status); - if (local_group) - goto next_group; - - - if (update_sd_pick_busiest(env, sds, sg, sgs)) { + if (!local_group && update_sd_pick_busiest(env, sds, sg, sgs)) { sds->busiest = sg; sds->busiest_stat = *sgs; } -next_group: /* Now, start updating sd_lb_stats */ sds->total_load += sgs->group_load; sds->total_capacity += sgs->group_capacity; @@ -10691,7 +10684,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s */ if (local->group_type == group_has_spare) { if ((busiest->group_type > group_fully_busy) && - !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) { + !(env->sd->flags & SD_SHARE_LLC)) { /* * If busiest is overloaded, try to fill spare * capacity. This might end up creating spare capacity @@ -11038,10 +11031,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, * If balancing between cores, let lower priority CPUs help * SMT cores with more than one busy sibling. */ - if ((env->sd->flags & SD_ASYM_PACKING) && - sched_use_asym_prio(env->sd, i) && - sched_asym_prefer(i, env->dst_cpu) && - nr_running == 1) + if (sched_asym(env->sd, i, env->dst_cpu) && nr_running == 1) continue; switch (env->migration_type) { @@ -11137,8 +11127,7 @@ asym_active_balance(struct lb_env *env) * the lower priority @env::dst_cpu help it. Do not follow * CPU priority. */ - return env->idle != CPU_NOT_IDLE && (env->sd->flags & SD_ASYM_PACKING) && - sched_use_asym_prio(env->sd, env->dst_cpu) && + return env->idle != CPU_NOT_IDLE && sched_use_asym_prio(env->sd, env->dst_cpu) && (sched_asym_prefer(env->dst_cpu, env->src_cpu) || !sched_use_asym_prio(env->sd, env->src_cpu)); } @@ -11910,8 +11899,7 @@ static void nohz_balancer_kick(struct rq *rq) * preferred CPU must be idle. */ for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) { - if (sched_use_asym_prio(sd, i) && - sched_asym_prefer(i, cpu)) { + if (sched_asym(sd, i, cpu)) { flags = NOHZ_STATS_KICK | NOHZ_BALANCE_KICK; goto unlock; } diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 31231925f1ec..6135fbe83d68 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -81,6 +81,25 @@ void __weak arch_cpu_idle(void) cpu_idle_force_poll = 1; } +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST_IDLE +DEFINE_STATIC_KEY_FALSE(arch_needs_tick_broadcast); + +static inline void cond_tick_broadcast_enter(void) +{ + if (static_branch_unlikely(&arch_needs_tick_broadcast)) + tick_broadcast_enter(); +} + +static inline void cond_tick_broadcast_exit(void) +{ + if (static_branch_unlikely(&arch_needs_tick_broadcast)) + tick_broadcast_exit(); +} +#else +static inline void cond_tick_broadcast_enter(void) { } +static inline void cond_tick_broadcast_exit(void) { } +#endif + /** * default_idle_call - Default CPU idle routine. * @@ -90,6 +109,7 @@ void __cpuidle default_idle_call(void) { instrumentation_begin(); if (!current_clr_polling_and_test()) { + cond_tick_broadcast_enter(); trace_cpu_idle(1, smp_processor_id()); stop_critical_timings(); @@ -99,6 +119,7 @@ void __cpuidle default_idle_call(void) start_critical_timings(); trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); + cond_tick_broadcast_exit(); } local_irq_enable(); instrumentation_end(); @@ -291,7 +312,6 @@ static void do_idle(void) local_irq_disable(); if (cpu_is_offline(cpu)) { - tick_nohz_idle_stop_tick(); cpuhp_report_idle_dead(); arch_cpu_idle_dead(); } diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 2ad881d07752..4e715b9b278e 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -162,6 +162,9 @@ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ | MEMBARRIER_CMD_GET_REGISTRATIONS) +static DEFINE_MUTEX(membarrier_ipi_mutex); +#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex) + static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ @@ -259,6 +262,7 @@ static int membarrier_global_expedited(void) if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { @@ -347,6 +351,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); if (cpu_id >= 0) { @@ -460,6 +465,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) * between threads which are users of @mm has its membarrier state * updated. */ + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 001fe047bd5d..d2242679239e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -3136,7 +3136,7 @@ static inline bool uclamp_rq_is_idle(struct rq *rq) #ifdef CONFIG_HAVE_SCHED_AVG_IRQ static inline unsigned long cpu_util_irq(struct rq *rq) { - return rq->avg_irq.util_avg; + return READ_ONCE(rq->avg_irq.util_avg); } static inline diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 10d1391e7416..99ea5986038c 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -657,13 +657,13 @@ static void destroy_sched_domains(struct sched_domain *sd) } /* - * Keep a special pointer to the highest sched_domain that has - * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this - * allows us to avoid some pointer chasing select_idle_sibling(). + * Keep a special pointer to the highest sched_domain that has SD_SHARE_LLC set + * (Last Level Cache Domain) for this allows us to avoid some pointer chasing + * select_idle_sibling(). * - * Also keep a unique ID per domain (we use the first CPU number in - * the cpumask of the domain), this allows us to quickly tell if - * two CPUs are in the same cache domain, see cpus_share_cache(). + * Also keep a unique ID per domain (we use the first CPU number in the cpumask + * of the domain), this allows us to quickly tell if two CPUs are in the same + * cache domain, see cpus_share_cache(). */ DEFINE_PER_CPU(struct sched_domain __rcu *, sd_llc); DEFINE_PER_CPU(int, sd_llc_size); @@ -684,7 +684,7 @@ static void update_top_cache_domain(int cpu) int id = cpu; int size = 1; - sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); + sd = highest_flag_domain(cpu, SD_SHARE_LLC); if (sd) { id = cpumask_first(sched_domain_span(sd)); size = cpumask_weight(sched_domain_span(sd)); @@ -1551,11 +1551,12 @@ static struct cpumask ***sched_domains_numa_masks; * * These flags are purely descriptive of the topology and do not prescribe * behaviour. Behaviour is artificial and mapped in the below sd_init() - * function: + * function. For details, see include/linux/sched/sd_flags.h. * - * SD_SHARE_CPUCAPACITY - describes SMT topologies - * SD_SHARE_PKG_RESOURCES - describes shared caches - * SD_NUMA - describes NUMA topologies + * SD_SHARE_CPUCAPACITY + * SD_SHARE_LLC + * SD_CLUSTER + * SD_NUMA * * Odd one out, which beside describing the topology has a quirk also * prescribes the desired behaviour that goes along with it: @@ -1565,7 +1566,7 @@ static struct cpumask ***sched_domains_numa_masks; #define TOPOLOGY_SD_FLAGS \ (SD_SHARE_CPUCAPACITY | \ SD_CLUSTER | \ - SD_SHARE_PKG_RESOURCES | \ + SD_SHARE_LLC | \ SD_NUMA | \ SD_ASYM_PACKING) @@ -1608,7 +1609,7 @@ sd_init(struct sched_domain_topology_level *tl, | 0*SD_BALANCE_WAKE | 1*SD_WAKE_AFFINE | 0*SD_SHARE_CPUCAPACITY - | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SHARE_LLC | 0*SD_SERIALIZE | 1*SD_PREFER_SIBLING | 0*SD_NUMA @@ -1645,7 +1646,7 @@ sd_init(struct sched_domain_topology_level *tl, if (sd->flags & SD_SHARE_CPUCAPACITY) { sd->imbalance_pct = 110; - } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + } else if (sd->flags & SD_SHARE_LLC) { sd->imbalance_pct = 117; sd->cache_nice_tries = 1; @@ -1670,7 +1671,7 @@ sd_init(struct sched_domain_topology_level *tl, * For all levels sharing cache; connect a sched_domain_shared * instance. */ - if (sd->flags & SD_SHARE_PKG_RESOURCES) { + if (sd->flags & SD_SHARE_LLC) { sd->shared = *per_cpu_ptr(sdd->sds, sd_id); atomic_inc(&sd->shared->ref); atomic_set(&sd->shared->nr_busy_cpus, sd_weight); @@ -2445,8 +2446,8 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { struct sched_domain *child = sd->child; - if (!(sd->flags & SD_SHARE_PKG_RESOURCES) && child && - (child->flags & SD_SHARE_PKG_RESOURCES)) { + if (!(sd->flags & SD_SHARE_LLC) && child && + (child->flags & SD_SHARE_LLC)) { struct sched_domain __rcu *top_p; unsigned int nr_llcs; diff --git a/kernel/signal.c b/kernel/signal.c index c9c57d053ce4..7bdbcf1b78d0 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -47,6 +47,7 @@ #include <linux/cgroup.h> #include <linux/audit.h> #include <linux/sysctl.h> +#include <uapi/linux/pidfd.h> #define CREATE_TRACE_POINTS #include <trace/events/signal.h> @@ -1436,7 +1437,8 @@ void lockdep_assert_task_sighand_held(struct task_struct *task) #endif /* - * send signal info to all the members of a group + * send signal info to all the members of a thread group or to the + * individual thread if type == PIDTYPE_PID. */ int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type) @@ -1478,7 +1480,8 @@ int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) return ret; } -int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) +static int kill_pid_info_type(int sig, struct kernel_siginfo *info, + struct pid *pid, enum pid_type type) { int error = -ESRCH; struct task_struct *p; @@ -1487,11 +1490,10 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) - error = group_send_sig_info(sig, info, p, PIDTYPE_TGID); + error = group_send_sig_info(sig, info, p, type); rcu_read_unlock(); if (likely(!p || error != -ESRCH)) return error; - /* * The task was unhashed in between, try again. If it * is dead, pid_task() will return NULL, if we race with @@ -1500,6 +1502,11 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) } } +int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) +{ + return kill_pid_info_type(sig, info, pid, PIDTYPE_TGID); +} + static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid) { int error; @@ -1898,16 +1905,19 @@ int send_sig_fault_trapno(int sig, int code, void __user *addr, int trapno, return send_sig_info(info.si_signo, &info, t); } -int kill_pgrp(struct pid *pid, int sig, int priv) +static int kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) { int ret; - read_lock(&tasklist_lock); - ret = __kill_pgrp_info(sig, __si_special(priv), pid); + ret = __kill_pgrp_info(sig, info, pgrp); read_unlock(&tasklist_lock); - return ret; } + +int kill_pgrp(struct pid *pid, int sig, int priv) +{ + return kill_pgrp_info(sig, __si_special(priv), pid); +} EXPORT_SYMBOL(kill_pgrp); int kill_pid(struct pid *pid, int sig, int priv) @@ -2019,13 +2029,14 @@ ret: return ret; } -static void do_notify_pidfd(struct task_struct *task) +void do_notify_pidfd(struct task_struct *task) { - struct pid *pid; + struct pid *pid = task_pid(task); WARN_ON(task->exit_state == 0); - pid = task_pid(task); - wake_up_all(&pid->wait_pidfd); + + __wake_up(&pid->wait_pidfd, TASK_NORMAL, 0, + poll_to_key(EPOLLIN | EPOLLRDNORM)); } /* @@ -2050,9 +2061,12 @@ bool do_notify_parent(struct task_struct *tsk, int sig) WARN_ON_ONCE(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); - - /* Wake up all pidfd waiters */ - do_notify_pidfd(tsk); + /* + * tsk is a group leader and has no threads, wake up the + * non-PIDFD_THREAD waiters. + */ + if (thread_group_empty(tsk)) + do_notify_pidfd(tsk); if (sig != SIGCHLD) { /* @@ -2727,12 +2741,15 @@ relock: /* Has this task already been marked for death? */ if ((signal->flags & SIGNAL_GROUP_EXIT) || signal->group_exec_task) { - clear_siginfo(&ksig->info); - ksig->info.si_signo = signr = SIGKILL; + signr = SIGKILL; sigdelset(¤t->pending.signal, SIGKILL); trace_signal_deliver(SIGKILL, SEND_SIG_NOINFO, - &sighand->action[SIGKILL - 1]); + &sighand->action[SIGKILL-1]); recalc_sigpending(); + /* + * implies do_group_exit() or return to PF_USER_WORKER, + * no need to initialize ksig->info/etc. + */ goto fatal; } @@ -2842,7 +2859,7 @@ relock: spin_lock_irq(&sighand->siglock); } - if (likely(do_signal_stop(ksig->info.si_signo))) { + if (likely(do_signal_stop(signr))) { /* It released the siglock. */ goto relock; } @@ -2866,7 +2883,7 @@ relock: if (sig_kernel_coredump(signr)) { if (print_fatal_signals) - print_fatal_signal(ksig->info.si_signo); + print_fatal_signal(signr); proc_coredump_connector(current); /* * If it was able to dump core, this kills all @@ -2881,8 +2898,9 @@ relock: /* * PF_USER_WORKER threads will catch and exit on fatal signals - * themselves. They have cleanup that must be performed, so - * we cannot call do_exit() on their behalf. + * themselves. They have cleanup that must be performed, so we + * cannot call do_exit() on their behalf. Note that ksig won't + * be properly initialized, PF_USER_WORKER's shouldn't use it. */ if (current->flags & PF_USER_WORKER) goto out; @@ -2890,17 +2908,17 @@ relock: /* * Death signals, no core dump. */ - do_group_exit(ksig->info.si_signo); + do_group_exit(signr); /* NOTREACHED */ } spin_unlock_irq(&sighand->siglock); -out: + ksig->sig = signr; - if (!(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS)) + if (signr && !(ksig->ka.sa.sa_flags & SA_EXPOSE_TAGBITS)) hide_si_addr_tag_bits(ksig); - - return ksig->sig > 0; +out: + return signr > 0; } /** @@ -3789,12 +3807,13 @@ COMPAT_SYSCALL_DEFINE4(rt_sigtimedwait_time32, compat_sigset_t __user *, uthese, #endif #endif -static inline void prepare_kill_siginfo(int sig, struct kernel_siginfo *info) +static void prepare_kill_siginfo(int sig, struct kernel_siginfo *info, + enum pid_type type) { clear_siginfo(info); info->si_signo = sig; info->si_errno = 0; - info->si_code = SI_USER; + info->si_code = (type == PIDTYPE_PID) ? SI_TKILL : SI_USER; info->si_pid = task_tgid_vnr(current); info->si_uid = from_kuid_munged(current_user_ns(), current_uid()); } @@ -3808,7 +3827,7 @@ SYSCALL_DEFINE2(kill, pid_t, pid, int, sig) { struct kernel_siginfo info; - prepare_kill_siginfo(sig, &info); + prepare_kill_siginfo(sig, &info, PIDTYPE_TGID); return kill_something_info(sig, &info, pid); } @@ -3861,6 +3880,10 @@ static struct pid *pidfd_to_pid(const struct file *file) return tgid_pidfd_to_pid(file); } +#define PIDFD_SEND_SIGNAL_FLAGS \ + (PIDFD_SIGNAL_THREAD | PIDFD_SIGNAL_THREAD_GROUP | \ + PIDFD_SIGNAL_PROCESS_GROUP) + /** * sys_pidfd_send_signal - Signal a process through a pidfd * @pidfd: file descriptor of the process @@ -3868,14 +3891,10 @@ static struct pid *pidfd_to_pid(const struct file *file) * @info: signal info * @flags: future flags * - * The syscall currently only signals via PIDTYPE_PID which covers - * kill(<positive-pid>, <signal>. It does not signal threads or process - * groups. - * In order to extend the syscall to threads and process groups the @flags - * argument should be used. In essence, the @flags argument will determine - * what is signaled and not the file descriptor itself. Put in other words, - * grouping is a property of the flags argument not a property of the file - * descriptor. + * Send the signal to the thread group or to the individual thread depending + * on PIDFD_THREAD. + * In the future extension to @flags may be used to override the default scope + * of @pidfd. * * Return: 0 on success, negative errno on failure */ @@ -3886,9 +3905,14 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, struct fd f; struct pid *pid; kernel_siginfo_t kinfo; + enum pid_type type; /* Enforce flags be set to 0 until we add an extension. */ - if (flags) + if (flags & ~PIDFD_SEND_SIGNAL_FLAGS) + return -EINVAL; + + /* Ensure that only a single signal scope determining flag is set. */ + if (hweight32(flags & PIDFD_SEND_SIGNAL_FLAGS) > 1) return -EINVAL; f = fdget(pidfd); @@ -3906,6 +3930,25 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (!access_pidfd_pidns(pid)) goto err; + switch (flags) { + case 0: + /* Infer scope from the type of pidfd. */ + if (f.file->f_flags & PIDFD_THREAD) + type = PIDTYPE_PID; + else + type = PIDTYPE_TGID; + break; + case PIDFD_SIGNAL_THREAD: + type = PIDTYPE_PID; + break; + case PIDFD_SIGNAL_THREAD_GROUP: + type = PIDTYPE_TGID; + break; + case PIDFD_SIGNAL_PROCESS_GROUP: + type = PIDTYPE_PGID; + break; + } + if (info) { ret = copy_siginfo_from_user_any(&kinfo, info); if (unlikely(ret)) @@ -3917,15 +3960,17 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, /* Only allow sending arbitrary signals to yourself. */ ret = -EPERM; - if ((task_pid(current) != pid) && + if ((task_pid(current) != pid || type > PIDTYPE_TGID) && (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) goto err; } else { - prepare_kill_siginfo(sig, &kinfo); + prepare_kill_siginfo(sig, &kinfo, type); } - ret = kill_pid_info(sig, &kinfo, pid); - + if (type == PIDTYPE_PGID) + ret = kill_pgrp_info(sig, &kinfo, pid); + else + ret = kill_pid_info_type(sig, &kinfo, pid, type); err: fdput(f); return ret; @@ -3965,12 +4010,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig) { struct kernel_siginfo info; - clear_siginfo(&info); - info.si_signo = sig; - info.si_errno = 0; - info.si_code = SI_TKILL; - info.si_pid = task_tgid_vnr(current); - info.si_uid = from_kuid_munged(current_user_ns(), current_uid()); + prepare_kill_siginfo(sig, &info, PIDTYPE_PID); return do_send_specific(tgid, pid, sig, &info); } diff --git a/kernel/softirq.c b/kernel/softirq.c index 210cf5f8d92c..b315b21fb28c 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -27,6 +27,7 @@ #include <linux/tick.h> #include <linux/irq.h> #include <linux/wait_bit.h> +#include <linux/workqueue.h> #include <asm/softirq_stack.h> @@ -802,11 +803,13 @@ static void tasklet_action_common(struct softirq_action *a, static __latent_entropy void tasklet_action(struct softirq_action *a) { + workqueue_softirq_action(false); tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); } static __latent_entropy void tasklet_hi_action(struct softirq_action *a) { + workqueue_softirq_action(true); tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); } @@ -929,6 +932,8 @@ static void run_ksoftirqd(unsigned int cpu) #ifdef CONFIG_HOTPLUG_CPU static int takeover_tasklets(unsigned int cpu) { + workqueue_softirq_dead(cpu); + /* CPU is dead, so no lock needed. */ local_irq_disable(); diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig index bae8f11070be..fc3b1a06c981 100644 --- a/kernel/time/Kconfig +++ b/kernel/time/Kconfig @@ -39,6 +39,11 @@ config GENERIC_CLOCKEVENTS_BROADCAST bool depends on GENERIC_CLOCKEVENTS +# Handle broadcast in default_idle_call() +config GENERIC_CLOCKEVENTS_BROADCAST_IDLE + bool + depends on GENERIC_CLOCKEVENTS_BROADCAST + # Automatically adjust the min. reprogramming time for # clock event device config GENERIC_CLOCKEVENTS_MIN_ADJUST diff --git a/kernel/time/Makefile b/kernel/time/Makefile index 7e875e63ff3b..4af2a264a160 100644 --- a/kernel/time/Makefile +++ b/kernel/time/Makefile @@ -17,6 +17,9 @@ endif obj-$(CONFIG_GENERIC_SCHED_CLOCK) += sched_clock.o obj-$(CONFIG_TICK_ONESHOT) += tick-oneshot.o tick-sched.o obj-$(CONFIG_LEGACY_TIMER_TICK) += tick-legacy.o +ifeq ($(CONFIG_SMP),y) + obj-$(CONFIG_NO_HZ_COMMON) += timer_migration.o +endif obj-$(CONFIG_HAVE_GENERIC_VDSO) += vsyscall.o obj-$(CONFIG_DEBUG_FS) += timekeeping_debug.o obj-$(CONFIG_TEST_UDELAY) += test_udelay.o diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c index 960143b183cd..a7ca458cdd9c 100644 --- a/kernel/time/clockevents.c +++ b/kernel/time/clockevents.c @@ -659,7 +659,7 @@ void tick_cleanup_dead_cpu(int cpu) #endif #ifdef CONFIG_SYSFS -static struct bus_type clockevents_subsys = { +static const struct bus_type clockevents_subsys = { .name = "clockevents", .dev_name = "clockevent", }; diff --git a/kernel/time/clocksource-wdtest.c b/kernel/time/clocksource-wdtest.c index df922f49d171..d06185e054ea 100644 --- a/kernel/time/clocksource-wdtest.c +++ b/kernel/time/clocksource-wdtest.c @@ -104,8 +104,8 @@ static void wdtest_ktime_clocksource_reset(void) static int wdtest_func(void *arg) { unsigned long j1, j2; + int i, max_retries; char *s; - int i; schedule_timeout_uninterruptible(holdoff * HZ); @@ -139,18 +139,19 @@ static int wdtest_func(void *arg) WARN_ON_ONCE(time_before(j2, j1 + NSEC_PER_USEC)); /* Verify tsc-like stability with various numbers of errors injected. */ - for (i = 0; i <= max_cswd_read_retries + 1; i++) { - if (i <= 1 && i < max_cswd_read_retries) + max_retries = clocksource_get_max_watchdog_retry(); + for (i = 0; i <= max_retries + 1; i++) { + if (i <= 1 && i < max_retries) s = ""; - else if (i <= max_cswd_read_retries) + else if (i <= max_retries) s = ", expect message"; else s = ", expect clock skew"; - pr_info("--- Watchdog with %dx error injection, %lu retries%s.\n", i, max_cswd_read_retries, s); + pr_info("--- Watchdog with %dx error injection, %d retries%s.\n", i, max_retries, s); WRITE_ONCE(wdtest_ktime_read_ndelays, i); schedule_timeout_uninterruptible(2 * HZ); WARN_ON_ONCE(READ_ONCE(wdtest_ktime_read_ndelays)); - WARN_ON_ONCE((i <= max_cswd_read_retries) != + WARN_ON_ONCE((i <= max_retries) != !(clocksource_wdtest_ktime.flags & CLOCK_SOURCE_UNSTABLE)); wdtest_ktime_clocksource_reset(); } diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c index 3052b1f1168e..e5b260aa0e02 100644 --- a/kernel/time/clocksource.c +++ b/kernel/time/clocksource.c @@ -210,9 +210,6 @@ void clocksource_mark_unstable(struct clocksource *cs) spin_unlock_irqrestore(&watchdog_lock, flags); } -ulong max_cswd_read_retries = 2; -module_param(max_cswd_read_retries, ulong, 0644); -EXPORT_SYMBOL_GPL(max_cswd_read_retries); static int verify_n_cpus = 8; module_param(verify_n_cpus, int, 0644); @@ -224,11 +221,12 @@ enum wd_read_status { static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, u64 *wdnow) { - unsigned int nretries; + unsigned int nretries, max_retries; u64 wd_end, wd_end2, wd_delta; int64_t wd_delay, wd_seq_delay; - for (nretries = 0; nretries <= max_cswd_read_retries; nretries++) { + max_retries = clocksource_get_max_watchdog_retry(); + for (nretries = 0; nretries <= max_retries; nretries++) { local_irq_disable(); *wdnow = watchdog->read(watchdog); *csnow = cs->read(cs); @@ -240,7 +238,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow, wd_delay = clocksource_cyc2ns(wd_delta, watchdog->mult, watchdog->shift); if (wd_delay <= WATCHDOG_MAX_SKEW) { - if (nretries > 1 || nretries >= max_cswd_read_retries) { + if (nretries > 1 || nretries >= max_retries) { pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n", smp_processor_id(), watchdog->name, nretries); } @@ -1468,7 +1466,7 @@ static struct attribute *clocksource_attrs[] = { }; ATTRIBUTE_GROUPS(clocksource); -static struct bus_type clocksource_subsys = { +static const struct bus_type clocksource_subsys = { .name = "clocksource", .dev_name = "clocksource", }; diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index edb0f821dcea..70625dff62ce 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -38,6 +38,7 @@ #include <linux/sched/deadline.h> #include <linux/sched/nohz.h> #include <linux/sched/debug.h> +#include <linux/sched/isolation.h> #include <linux/timer.h> #include <linux/freezer.h> #include <linux/compat.h> @@ -746,7 +747,7 @@ static void hrtimer_switch_to_hres(void) base->hres_active = 1; hrtimer_resolution = HIGH_RES_NSEC; - tick_setup_sched_timer(); + tick_setup_sched_timer(true); /* "Retrigger" the interrupt to get things going */ retrigger_next_event(NULL); } @@ -1021,21 +1022,23 @@ void unlock_hrtimer_base(const struct hrtimer *timer, unsigned long *flags) } /** - * hrtimer_forward - forward the timer expiry + * hrtimer_forward() - forward the timer expiry * @timer: hrtimer to forward * @now: forward past this time * @interval: the interval to forward * * Forward the timer expiry so it will expire in the future. - * Returns the number of overruns. * - * Can be safely called from the callback function of @timer. If - * called from other contexts @timer must neither be enqueued nor - * running the callback and the caller needs to take care of - * serialization. + * .. note:: + * This only updates the timer expiry value and does not requeue the timer. * - * Note: This only updates the timer expiry value and does not requeue - * the timer. + * There is also a variant of the function hrtimer_forward_now(). + * + * Context: Can be safely called from the callback function of @timer. If called + * from other contexts @timer must neither be enqueued nor running the + * callback and the caller needs to take care of serialization. + * + * Return: The number of overruns are returned. */ u64 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval) { @@ -2223,10 +2226,8 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, int hrtimers_cpu_dying(unsigned int dying_cpu) { + int i, ncpu = cpumask_any_and(cpu_active_mask, housekeeping_cpumask(HK_TYPE_TIMER)); struct hrtimer_cpu_base *old_base, *new_base; - int i, ncpu = cpumask_first(cpu_active_mask); - - tick_cancel_sched_timer(dying_cpu); old_base = this_cpu_ptr(&hrtimer_bases); new_base = &per_cpu(hrtimer_bases, ncpu); diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index e9138cd7a0f5..fb0fdec8719a 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -111,15 +111,13 @@ void tick_handle_periodic(struct clock_event_device *dev) tick_periodic(cpu); -#if defined(CONFIG_HIGH_RES_TIMERS) || defined(CONFIG_NO_HZ_COMMON) /* * The cpu might have transitioned to HIGHRES or NOHZ mode via * update_process_times() -> run_local_timers() -> * hrtimer_run_queues(). */ - if (dev->event_handler != tick_handle_periodic) + if (IS_ENABLED(CONFIG_TICK_ONESHOT) && dev->event_handler != tick_handle_periodic) return; -#endif if (!clockevent_state_oneshot(dev)) return; @@ -398,16 +396,31 @@ int tick_broadcast_oneshot_control(enum tick_broadcast_state state) EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control); #ifdef CONFIG_HOTPLUG_CPU +void tick_assert_timekeeping_handover(void) +{ + WARN_ON_ONCE(tick_do_timer_cpu == smp_processor_id()); +} /* - * Transfer the do_timer job away from a dying cpu. - * - * Called with interrupts disabled. No locking required. If - * tick_do_timer_cpu is owned by this cpu, nothing can change it. + * Stop the tick and transfer the timekeeping job away from a dying cpu. */ -void tick_handover_do_timer(void) +int tick_cpu_dying(unsigned int dying_cpu) { - if (tick_do_timer_cpu == smp_processor_id()) + /* + * If the current CPU is the timekeeper, it's the only one that + * can safely hand over its duty. Also all online CPUs are in + * stop machine, guaranteed not to be idle, therefore it's safe + * to pick any online successor. + */ + if (tick_do_timer_cpu == dying_cpu) tick_do_timer_cpu = cpumask_first(cpu_online_mask); + + /* Make sure the CPU won't try to retake the timekeeping duty */ + tick_sched_timer_dying(dying_cpu); + + /* Remove CPU from timer broadcasting */ + tick_offline_cpu(dying_cpu); + + return 0; } /* diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h index 481b7ab65e2c..5f2105e637bd 100644 --- a/kernel/time/tick-internal.h +++ b/kernel/time/tick-internal.h @@ -8,6 +8,11 @@ #include "timekeeping.h" #include "tick-sched.h" +struct timer_events { + u64 local; + u64 global; +}; + #ifdef CONFIG_GENERIC_CLOCKEVENTS # define TICK_DO_TIMER_NONE -1 @@ -137,8 +142,10 @@ static inline bool tick_broadcast_oneshot_available(void) { return tick_oneshot_ #endif /* !(BROADCAST && ONESHOT) */ #if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_HOTPLUG_CPU) +extern void tick_offline_cpu(unsigned int cpu); extern void tick_broadcast_offline(unsigned int cpu); #else +static inline void tick_offline_cpu(unsigned int cpu) { } static inline void tick_broadcast_offline(unsigned int cpu) { } #endif @@ -152,8 +159,16 @@ static inline void tick_nohz_init(void) { } #ifdef CONFIG_NO_HZ_COMMON extern unsigned long tick_nohz_active; extern void timers_update_nohz(void); +extern u64 get_jiffies_update(unsigned long *basej); # ifdef CONFIG_SMP extern struct static_key_false timers_migration_enabled; +extern void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, + struct timer_events *tevt, + unsigned int cpu); +extern void timer_lock_remote_bases(unsigned int cpu); +extern void timer_unlock_remote_bases(unsigned int cpu); +extern bool timer_base_is_idle(void); +extern void timer_expire_remote(unsigned int cpu); # endif #else /* CONFIG_NO_HZ_COMMON */ static inline void timers_update_nohz(void) { } @@ -163,6 +178,7 @@ static inline void timers_update_nohz(void) { } DECLARE_PER_CPU(struct hrtimer_cpu_base, hrtimer_bases); extern u64 get_next_timer_interrupt(unsigned long basej, u64 basem); +u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle); void timer_clear_idle(void); #define CLOCK_SET_WALL \ diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 01fb50c1b17e..269e21590df5 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -43,7 +43,6 @@ struct tick_sched *tick_get_tick_sched(int cpu) return &per_cpu(tick_cpu_sched, cpu); } -#if defined(CONFIG_NO_HZ_COMMON) || defined(CONFIG_HIGH_RES_TIMERS) /* * The time when the last jiffy update happened. Write access must hold * jiffies_lock and jiffies_seq. tick_nohz_next_event() needs to get a @@ -181,13 +180,32 @@ static ktime_t tick_init_jiffy_update(void) return period; } +static inline int tick_sched_flag_test(struct tick_sched *ts, + unsigned long flag) +{ + return !!(ts->flags & flag); +} + +static inline void tick_sched_flag_set(struct tick_sched *ts, + unsigned long flag) +{ + lockdep_assert_irqs_disabled(); + ts->flags |= flag; +} + +static inline void tick_sched_flag_clear(struct tick_sched *ts, + unsigned long flag) +{ + lockdep_assert_irqs_disabled(); + ts->flags &= ~flag; +} + #define MAX_STALLED_JIFFIES 5 static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) { int cpu = smp_processor_id(); -#ifdef CONFIG_NO_HZ_COMMON /* * Check if the do_timer duty was dropped. We don't care about * concurrency: This happens only when the CPU in charge went @@ -198,13 +216,13 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) * If nohz_full is enabled, this should not happen because the * 'tick_do_timer_cpu' CPU never relinquishes. */ - if (unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && + unlikely(tick_do_timer_cpu == TICK_DO_TIMER_NONE)) { #ifdef CONFIG_NO_HZ_FULL WARN_ON_ONCE(tick_nohz_full_running); #endif tick_do_timer_cpu = cpu; } -#endif /* Check if jiffies need an update */ if (tick_do_timer_cpu == cpu) @@ -225,13 +243,12 @@ static void tick_sched_do_timer(struct tick_sched *ts, ktime_t now) } } - if (ts->inidle) + if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) ts->got_idle_tick = 1; } static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) { -#ifdef CONFIG_NO_HZ_COMMON /* * When we are idle and the tick is stopped, we have to touch * the watchdog as we might not schedule for a really long @@ -240,7 +257,8 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) * idle" jiffy stamp so the idle accounting adjustment we do * when we go busy again does not account too many ticks. */ - if (ts->tick_stopped) { + if (IS_ENABLED(CONFIG_NO_HZ_COMMON) && + tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { touch_softlockup_watchdog_sched(); if (is_idle_task(current)) ts->idle_jiffies++; @@ -251,11 +269,52 @@ static void tick_sched_handle(struct tick_sched *ts, struct pt_regs *regs) */ ts->next_tick = 0; } -#endif + update_process_times(user_mode(regs)); profile_tick(CPU_PROFILING); } -#endif + +/* + * We rearm the timer until we get disabled by the idle code. + * Called with interrupts disabled. + */ +static enum hrtimer_restart tick_nohz_handler(struct hrtimer *timer) +{ + struct tick_sched *ts = container_of(timer, struct tick_sched, sched_timer); + struct pt_regs *regs = get_irq_regs(); + ktime_t now = ktime_get(); + + tick_sched_do_timer(ts, now); + + /* + * Do not call when we are not in IRQ context and have + * no valid 'regs' pointer + */ + if (regs) + tick_sched_handle(ts, regs); + else + ts->next_tick = 0; + + /* + * In dynticks mode, tick reprogram is deferred: + * - to the idle task if in dynticks-idle + * - to IRQ exit if in full-dynticks. + */ + if (unlikely(tick_sched_flag_test(ts, TS_FLAG_STOPPED))) + return HRTIMER_NORESTART; + + hrtimer_forward(timer, now, TICK_NSEC); + + return HRTIMER_RESTART; +} + +static void tick_sched_timer_cancel(struct tick_sched *ts) +{ + if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) + hrtimer_cancel(&ts->sched_timer); + else if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) + tick_program_event(KTIME_MAX, 1); +} #ifdef CONFIG_NO_HZ_FULL cpumask_var_t tick_nohz_full_mask; @@ -529,7 +588,7 @@ void __tick_nohz_task_switch(void) ts = this_cpu_ptr(&tick_cpu_sched); - if (ts->tick_stopped) { + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { if (atomic_read(¤t->tick_dep_mask) || atomic_read(¤t->signal->tick_dep_mask)) tick_nohz_full_kick(); @@ -601,7 +660,7 @@ void __init tick_nohz_init(void) pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); } -#endif +#endif /* #ifdef CONFIG_NO_HZ_FULL */ /* * NOHZ - aka dynamic tick functionality @@ -626,14 +685,14 @@ bool tick_nohz_tick_stopped(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - return ts->tick_stopped; + return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } bool tick_nohz_tick_stopped_cpu(int cpu) { struct tick_sched *ts = per_cpu_ptr(&tick_cpu_sched, cpu); - return ts->tick_stopped; + return tick_sched_flag_test(ts, TS_FLAG_STOPPED); } /** @@ -663,7 +722,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) { ktime_t delta; - if (WARN_ON_ONCE(!ts->idle_active)) + if (WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE))) return; delta = ktime_sub(now, ts->idle_entrytime); @@ -675,7 +734,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now) ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta); ts->idle_entrytime = now; - ts->idle_active = 0; + tick_sched_flag_clear(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_wakeup_event(); @@ -685,7 +744,7 @@ static void tick_nohz_start_idle(struct tick_sched *ts) { write_seqcount_begin(&ts->idle_sleeptime_seq); ts->idle_entrytime = ktime_get(); - ts->idle_active = 1; + tick_sched_flag_set(ts, TS_FLAG_IDLE_ACTIVE); write_seqcount_end(&ts->idle_sleeptime_seq); sched_clock_idle_sleep_event(); @@ -707,7 +766,7 @@ static u64 get_cpu_sleep_time_us(struct tick_sched *ts, ktime_t *sleeptime, do { seq = read_seqcount_begin(&ts->idle_sleeptime_seq); - if (ts->idle_active && compute_delta) { + if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE) && compute_delta) { ktime_t delta = ktime_sub(now, ts->idle_entrytime); idle = ktime_add(*sleeptime, delta); @@ -780,7 +839,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now) /* Forward the time to expire in the future */ hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); } else { @@ -799,18 +858,40 @@ static inline bool local_timer_softirq_pending(void) return local_softirq_pending() & BIT(TIMER_SOFTIRQ); } -static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) +/* + * Read jiffies and the time when jiffies were updated last + */ +u64 get_jiffies_update(unsigned long *basej) { - u64 basemono, next_tick, delta, expires; unsigned long basejiff; unsigned int seq; + u64 basemono; - /* Read jiffies and the time when jiffies were updated last */ do { seq = read_seqcount_begin(&jiffies_seq); basemono = last_jiffies_update; basejiff = jiffies; } while (read_seqcount_retry(&jiffies_seq, seq)); + *basej = basejiff; + return basemono; +} + +/** + * tick_nohz_next_event() - return the clock monotonic based next event + * @ts: pointer to tick_sched struct + * @cpu: CPU number + * + * Return: + * *%0 - When the next event is a maximum of TICK_NSEC in the future + * and the tick is not stopped yet + * *%next_event - Next event based on clock monotonic + */ +static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) +{ + u64 basemono, next_tick, delta, expires; + unsigned long basejiff; + + basemono = get_jiffies_update(&basejiff); ts->last_jiffies = basejiff; ts->timer_expires_base = basemono; @@ -850,15 +931,10 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) delta = next_tick - basemono; if (delta <= (u64)TICK_NSEC) { /* - * Tell the timer code that the base is not idle, i.e. undo - * the effect of get_next_timer_interrupt(): - */ - timer_clear_idle(); - /* * We've not stopped the tick yet, and there's a timer in the * next period, so no point in stopping it either, bail. */ - if (!ts->tick_stopped) { + if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->timer_expires = 0; goto out; } @@ -871,7 +947,8 @@ static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu) */ delta = timekeeping_max_deferment(); if (cpu != tick_do_timer_cpu && - (tick_do_timer_cpu != TICK_DO_TIMER_NONE || !ts->do_timer_last)) + (tick_do_timer_cpu != TICK_DO_TIMER_NONE || + !tick_sched_flag_test(ts, TS_FLAG_DO_TIMER_LAST))) delta = KTIME_MAX; /* Calculate the next expiry time */ @@ -889,13 +966,39 @@ out: static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) { struct clock_event_device *dev = __this_cpu_read(tick_cpu_device.evtdev); + unsigned long basejiff = ts->last_jiffies; u64 basemono = ts->timer_expires_base; - u64 expires = ts->timer_expires; + bool timer_idle = tick_sched_flag_test(ts, TS_FLAG_STOPPED); + u64 expires; /* Make sure we won't be trying to stop it twice in a row. */ ts->timer_expires_base = 0; /* + * Now the tick should be stopped definitely - so the timer base needs + * to be marked idle as well to not miss a newly queued timer. + */ + expires = timer_base_try_to_set_idle(basejiff, basemono, &timer_idle); + if (expires > ts->timer_expires) { + /* + * This path could only happen when the first timer was removed + * between calculating the possible sleep length and now (when + * high resolution mode is not active, timer could also be a + * hrtimer). + * + * We have to stick to the original calculated expiry value to + * not stop the tick for too long with a shallow C-state (which + * was programmed by cpuidle because of an early next expiration + * value). + */ + expires = ts->timer_expires; + } + + /* If the timer base is not idle, retain the not yet stopped tick. */ + if (!timer_idle) + return; + + /* * If this CPU is the one which updates jiffies, then give up * the assignment and let it be taken by the CPU which runs * the tick timer next, which might be this CPU as well. If we @@ -905,13 +1008,13 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) */ if (cpu == tick_do_timer_cpu) { tick_do_timer_cpu = TICK_DO_TIMER_NONE; - ts->do_timer_last = 1; + tick_sched_flag_set(ts, TS_FLAG_DO_TIMER_LAST); } else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) { - ts->do_timer_last = 0; + tick_sched_flag_clear(ts, TS_FLAG_DO_TIMER_LAST); } /* Skip reprogram of event if it's not changed */ - if (ts->tick_stopped && (expires == ts->next_tick)) { + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED) && (expires == ts->next_tick)) { /* Sanity check: make sure clockevent is actually programmed */ if (expires == KTIME_MAX || ts->next_tick == hrtimer_get_expires(&ts->sched_timer)) return; @@ -929,12 +1032,12 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) * call we save the current tick time, so we can restart the * scheduler tick in tick_nohz_restart_sched_tick(). */ - if (!ts->tick_stopped) { + if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { calc_load_nohz_start(); quiet_vmstat(); ts->last_tick = hrtimer_get_expires(&ts->sched_timer); - ts->tick_stopped = 1; + tick_sched_flag_set(ts, TS_FLAG_STOPPED); trace_tick_stop(1, TICK_DEP_MASK_NONE); } @@ -945,14 +1048,11 @@ static void tick_nohz_stop_tick(struct tick_sched *ts, int cpu) * the tick timer. */ if (unlikely(expires == KTIME_MAX)) { - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) - hrtimer_cancel(&ts->sched_timer); - else - tick_program_event(KTIME_MAX, 1); + tick_sched_timer_cancel(ts); return; } - if (ts->nohz_mode == NOHZ_MODE_HIGHRES) { + if (tick_sched_flag_test(ts, TS_FLAG_HIGHRES)) { hrtimer_start(&ts->sched_timer, expires, HRTIMER_MODE_ABS_PINNED_HARD); } else { @@ -967,7 +1067,7 @@ static void tick_nohz_retain_tick(struct tick_sched *ts) } #ifdef CONFIG_NO_HZ_FULL -static void tick_nohz_stop_sched_tick(struct tick_sched *ts, int cpu) +static void tick_nohz_full_stop_tick(struct tick_sched *ts, int cpu) { if (tick_nohz_next_event(ts, cpu)) tick_nohz_stop_tick(ts, cpu); @@ -991,7 +1091,7 @@ static void tick_nohz_restart_sched_tick(struct tick_sched *ts, ktime_t now) touch_softlockup_watchdog_sched(); /* Cancel the scheduled timer and restore the tick: */ - ts->tick_stopped = 0; + tick_sched_flag_clear(ts, TS_FLAG_STOPPED); tick_nohz_restart(ts, now); } @@ -1002,8 +1102,8 @@ static void __tick_nohz_full_update_tick(struct tick_sched *ts, int cpu = smp_processor_id(); if (can_stop_full_tick(cpu, ts)) - tick_nohz_stop_sched_tick(ts, cpu); - else if (ts->tick_stopped) + tick_nohz_full_stop_tick(ts, cpu); + else if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_restart_sched_tick(ts, now); #endif } @@ -1013,7 +1113,7 @@ static void tick_nohz_full_update_tick(struct tick_sched *ts) if (!tick_nohz_full_cpu(smp_processor_id())) return; - if (!ts->tick_stopped && ts->nohz_mode == NOHZ_MODE_INACTIVE) + if (!tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return; __tick_nohz_full_update_tick(ts, ktime_get()); @@ -1060,25 +1160,9 @@ static bool report_idle_softirq(void) static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) { - /* - * If this CPU is offline and it is the one which updates - * jiffies, then give up the assignment and let it be taken by - * the CPU which runs the tick timer next. If we don't drop - * this here, the jiffies might be stale and do_timer() never - * gets invoked. - */ - if (unlikely(!cpu_online(cpu))) { - if (cpu == tick_do_timer_cpu) - tick_do_timer_cpu = TICK_DO_TIMER_NONE; - /* - * Make sure the CPU doesn't get fooled by obsolete tick - * deadline if it comes back online later. - */ - ts->next_tick = 0; - return false; - } + WARN_ON_ONCE(cpu_is_offline(cpu)); - if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE)) + if (unlikely(!tick_sched_flag_test(ts, TS_FLAG_NOHZ))) return false; if (need_resched()) @@ -1128,14 +1212,14 @@ void tick_nohz_idle_stop_tick(void) ts->idle_calls++; if (expires > 0LL) { - int was_stopped = ts->tick_stopped; + int was_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); tick_nohz_stop_tick(ts, cpu); ts->idle_sleeps++; ts->idle_expires = expires; - if (!was_stopped && ts->tick_stopped) { + if (!was_stopped && tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ts->idle_jiffies = ts->last_jiffies; nohz_balance_enter_idle(cpu); } @@ -1147,11 +1231,6 @@ void tick_nohz_idle_stop_tick(void) void tick_nohz_idle_retain_tick(void) { tick_nohz_retain_tick(this_cpu_ptr(&tick_cpu_sched)); - /* - * Undo the effect of get_next_timer_interrupt() called from - * tick_nohz_next_event(). - */ - timer_clear_idle(); } /** @@ -1171,7 +1250,7 @@ void tick_nohz_idle_enter(void) WARN_ON_ONCE(ts->timer_expires_base); - ts->inidle = 1; + tick_sched_flag_set(ts, TS_FLAG_INIDLE); tick_nohz_start_idle(ts); local_irq_enable(); @@ -1200,7 +1279,7 @@ void tick_nohz_irq_exit(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - if (ts->inidle) + if (tick_sched_flag_test(ts, TS_FLAG_INIDLE)) tick_nohz_start_idle(ts); else tick_nohz_full_update_tick(ts); @@ -1254,7 +1333,7 @@ ktime_t tick_nohz_get_sleep_length(ktime_t *delta_next) ktime_t now = ts->idle_entrytime; ktime_t next_event; - WARN_ON_ONCE(!ts->inidle); + WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); *delta_next = ktime_sub(dev->next_event, now); @@ -1326,7 +1405,7 @@ void tick_nohz_idle_restart_tick(void) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - if (ts->tick_stopped) { + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) { ktime_t now = ktime_get(); tick_nohz_restart_sched_tick(ts, now); tick_nohz_account_idle_time(ts, now); @@ -1367,12 +1446,12 @@ void tick_nohz_idle_exit(void) local_irq_disable(); - WARN_ON_ONCE(!ts->inidle); + WARN_ON_ONCE(!tick_sched_flag_test(ts, TS_FLAG_INIDLE)); WARN_ON_ONCE(ts->timer_expires_base); - ts->inidle = 0; - idle_active = ts->idle_active; - tick_stopped = ts->tick_stopped; + tick_sched_flag_clear(ts, TS_FLAG_INIDLE); + idle_active = tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE); + tick_stopped = tick_sched_flag_test(ts, TS_FLAG_STOPPED); if (idle_active || tick_stopped) now = ktime_get(); @@ -1391,38 +1470,22 @@ void tick_nohz_idle_exit(void) * at the clockevent level. hrtimer can't be used instead, because its * infrastructure actually relies on the tick itself as a backend in * low-resolution mode (see hrtimer_run_queues()). - * - * This low-resolution handler still makes use of some hrtimer APIs meanwhile - * for convenience with expiration calculation and forwarding. */ static void tick_nohz_lowres_handler(struct clock_event_device *dev) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - struct pt_regs *regs = get_irq_regs(); - ktime_t now = ktime_get(); dev->next_event = KTIME_MAX; - tick_sched_do_timer(ts, now); - tick_sched_handle(ts, regs); - - /* - * In dynticks mode, tick reprogram is deferred: - * - to the idle task if in dynticks-idle - * - to IRQ exit if in full-dynticks. - */ - if (likely(!ts->tick_stopped)) { - hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); + if (likely(tick_nohz_handler(&ts->sched_timer) == HRTIMER_RESTART)) tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); - } - } -static inline void tick_nohz_activate(struct tick_sched *ts, int mode) +static inline void tick_nohz_activate(struct tick_sched *ts) { if (!tick_nohz_enabled) return; - ts->nohz_mode = mode; + tick_sched_flag_set(ts, TS_FLAG_NOHZ); /* One update is enough */ if (!test_and_set_bit(0, &tick_nohz_active)) timers_update_nohz(); @@ -1433,9 +1496,6 @@ static inline void tick_nohz_activate(struct tick_sched *ts, int mode) */ static void tick_nohz_switch_to_nohz(void) { - struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - ktime_t next; - if (!tick_nohz_enabled) return; @@ -1444,16 +1504,9 @@ static void tick_nohz_switch_to_nohz(void) /* * Recycle the hrtimer in 'ts', so we can share the - * hrtimer_forward_now() function with the highres code. + * highres code. */ - hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - /* Get the next period */ - next = tick_init_jiffy_update(); - - hrtimer_set_expires(&ts->sched_timer, next); - hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); - tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); - tick_nohz_activate(ts, NOHZ_MODE_LOWRES); + tick_setup_sched_timer(false); } static inline void tick_nohz_irq_enter(void) @@ -1461,10 +1514,10 @@ static inline void tick_nohz_irq_enter(void) struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); ktime_t now; - if (!ts->idle_active && !ts->tick_stopped) + if (!tick_sched_flag_test(ts, TS_FLAG_STOPPED | TS_FLAG_IDLE_ACTIVE)) return; now = ktime_get(); - if (ts->idle_active) + if (tick_sched_flag_test(ts, TS_FLAG_IDLE_ACTIVE)) tick_nohz_stop_idle(ts, now); /* * If all CPUs are idle we may need to update a stale jiffies value. @@ -1473,7 +1526,7 @@ static inline void tick_nohz_irq_enter(void) * rare case (typically stop machine). So we must make sure we have a * last resort. */ - if (ts->tick_stopped) + if (tick_sched_flag_test(ts, TS_FLAG_STOPPED)) tick_nohz_update_jiffies(now); } @@ -1481,7 +1534,7 @@ static inline void tick_nohz_irq_enter(void) static inline void tick_nohz_switch_to_nohz(void) { } static inline void tick_nohz_irq_enter(void) { } -static inline void tick_nohz_activate(struct tick_sched *ts, int mode) { } +static inline void tick_nohz_activate(struct tick_sched *ts) { } #endif /* CONFIG_NO_HZ_COMMON */ @@ -1494,45 +1547,6 @@ void tick_irq_enter(void) tick_nohz_irq_enter(); } -/* - * High resolution timer specific code - */ -#ifdef CONFIG_HIGH_RES_TIMERS -/* - * We rearm the timer until we get disabled by the idle code. - * Called with interrupts disabled. - */ -static enum hrtimer_restart tick_nohz_highres_handler(struct hrtimer *timer) -{ - struct tick_sched *ts = - container_of(timer, struct tick_sched, sched_timer); - struct pt_regs *regs = get_irq_regs(); - ktime_t now = ktime_get(); - - tick_sched_do_timer(ts, now); - - /* - * Do not call when we are not in IRQ context and have - * no valid 'regs' pointer - */ - if (regs) - tick_sched_handle(ts, regs); - else - ts->next_tick = 0; - - /* - * In dynticks mode, tick reprogram is deferred: - * - to the idle task if in dynticks-idle - * - to IRQ exit if in full-dynticks. - */ - if (unlikely(ts->tick_stopped)) - return HRTIMER_NORESTART; - - hrtimer_forward(timer, now, TICK_NSEC); - - return HRTIMER_RESTART; -} - static int sched_skew_tick; static int __init skew_tick(char *str) @@ -1545,15 +1559,19 @@ early_param("skew_tick", skew_tick); /** * tick_setup_sched_timer - setup the tick emulation timer + * @mode: tick_nohz_mode to setup for */ -void tick_setup_sched_timer(void) +void tick_setup_sched_timer(bool hrtimer) { struct tick_sched *ts = this_cpu_ptr(&tick_cpu_sched); - ktime_t now = ktime_get(); /* Emulate tick processing via per-CPU hrtimers: */ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); - ts->sched_timer.function = tick_nohz_highres_handler; + + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) { + tick_sched_flag_set(ts, TS_FLAG_HIGHRES); + ts->sched_timer.function = tick_nohz_handler; + } /* Get the next period (per-CPU) */ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update()); @@ -1566,23 +1584,35 @@ void tick_setup_sched_timer(void) hrtimer_add_expires_ns(&ts->sched_timer, offset); } - hrtimer_forward(&ts->sched_timer, now, TICK_NSEC); - hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); - tick_nohz_activate(ts, NOHZ_MODE_HIGHRES); + hrtimer_forward_now(&ts->sched_timer, TICK_NSEC); + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && hrtimer) + hrtimer_start_expires(&ts->sched_timer, HRTIMER_MODE_ABS_PINNED_HARD); + else + tick_program_event(hrtimer_get_expires(&ts->sched_timer), 1); + tick_nohz_activate(ts); } -#endif /* HIGH_RES_TIMERS */ -#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS -void tick_cancel_sched_timer(int cpu) +/* + * Shut down the tick and make sure the CPU won't try to retake the timekeeping + * duty before disabling IRQs in idle for the last time. + */ +void tick_sched_timer_dying(int cpu) { + struct tick_device *td = &per_cpu(tick_cpu_device, cpu); struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu); + struct clock_event_device *dev = td->evtdev; ktime_t idle_sleeptime, iowait_sleeptime; unsigned long idle_calls, idle_sleeps; -# ifdef CONFIG_HIGH_RES_TIMERS - if (ts->sched_timer.base) - hrtimer_cancel(&ts->sched_timer); -# endif + /* This must happen before hrtimers are migrated! */ + tick_sched_timer_cancel(ts); + + /* + * If the clockevents doesn't support CLOCK_EVT_STATE_ONESHOT_STOPPED, + * make sure not to call low-res tick handler. + */ + if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) + dev->event_handler = clockevents_handle_noop; idle_sleeptime = ts->idle_sleeptime; iowait_sleeptime = ts->iowait_sleeptime; @@ -1594,7 +1624,6 @@ void tick_cancel_sched_timer(int cpu) ts->idle_calls = idle_calls; ts->idle_sleeps = idle_sleeps; } -#endif /* * Async notification about clocksource changes @@ -1632,7 +1661,7 @@ int tick_check_oneshot_change(int allow_nohz) if (!test_and_clear_bit(0, &ts->check_clocks)) return 0; - if (ts->nohz_mode != NOHZ_MODE_INACTIVE) + if (tick_sched_flag_test(ts, TS_FLAG_NOHZ)) return 0; if (!timekeeping_valid_for_hres() || !tick_is_oneshot_available()) diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h index 5ed5a9d41d5a..e11c4dc65bcb 100644 --- a/kernel/time/tick-sched.h +++ b/kernel/time/tick-sched.h @@ -14,20 +14,26 @@ struct tick_device { enum tick_device_mode mode; }; -enum tick_nohz_mode { - NOHZ_MODE_INACTIVE, - NOHZ_MODE_LOWRES, - NOHZ_MODE_HIGHRES, -}; +/* The CPU is in the tick idle mode */ +#define TS_FLAG_INIDLE BIT(0) +/* The idle tick has been stopped */ +#define TS_FLAG_STOPPED BIT(1) +/* + * Indicator that the CPU is actively in the tick idle mode; + * it is reset during irq handling phases. + */ +#define TS_FLAG_IDLE_ACTIVE BIT(2) +/* CPU was the last one doing do_timer before going idle */ +#define TS_FLAG_DO_TIMER_LAST BIT(3) +/* NO_HZ is enabled */ +#define TS_FLAG_NOHZ BIT(4) +/* High resolution tick mode */ +#define TS_FLAG_HIGHRES BIT(5) /** * struct tick_sched - sched tick emulation and no idle tick control/stats * - * @inidle: Indicator that the CPU is in the tick idle mode - * @tick_stopped: Indicator that the idle tick has been stopped - * @idle_active: Indicator that the CPU is actively in the tick idle mode; - * it is reset during irq handling phases. - * @do_timer_last: CPU was the last one doing do_timer before going idle + * @flags: State flags gathering the TS_FLAG_* features * @got_idle_tick: Tick timer function has run with @inidle set * @stalled_jiffies: Number of stalled jiffies detected across ticks * @last_tick_jiffies: Value of jiffies seen on last tick @@ -57,11 +63,7 @@ enum tick_nohz_mode { */ struct tick_sched { /* Common flags */ - unsigned int inidle : 1; - unsigned int tick_stopped : 1; - unsigned int idle_active : 1; - unsigned int do_timer_last : 1; - unsigned int got_idle_tick : 1; + unsigned long flags; /* Tick handling: jiffies stall check */ unsigned int stalled_jiffies; @@ -73,13 +75,13 @@ struct tick_sched { ktime_t next_tick; unsigned long idle_jiffies; ktime_t idle_waketime; + unsigned int got_idle_tick; /* Idle entry */ seqcount_t idle_sleeptime_seq; ktime_t idle_entrytime; /* Tick stop */ - enum tick_nohz_mode nohz_mode; unsigned long last_jiffies; u64 timer_expires_base; u64 timer_expires; @@ -102,11 +104,11 @@ struct tick_sched { extern struct tick_sched *tick_get_tick_sched(int cpu); -extern void tick_setup_sched_timer(void); -#if defined CONFIG_NO_HZ_COMMON || defined CONFIG_HIGH_RES_TIMERS -extern void tick_cancel_sched_timer(int cpu); +extern void tick_setup_sched_timer(bool hrtimer); +#if defined CONFIG_TICK_ONESHOT +extern void tick_sched_timer_dying(int cpu); #else -static inline void tick_cancel_sched_timer(int cpu) { } +static inline void tick_sched_timer_dying(int cpu) { } #endif #ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST diff --git a/kernel/time/time_test.c b/kernel/time/time_test.c index ca058c8af6ba..3e5d422dd15c 100644 --- a/kernel/time/time_test.c +++ b/kernel/time/time_test.c @@ -73,7 +73,7 @@ static void time64_to_tm_test_date_range(struct kunit *test) days = div_s64(secs, 86400); - #define FAIL_MSG "%05ld/%02d/%02d (%2d) : %ld", \ + #define FAIL_MSG "%05ld/%02d/%02d (%2d) : %lld", \ year, month, mdday, yday, days KUNIT_ASSERT_EQ_MSG(test, year - 1900, result.tm_year, FAIL_MSG); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 266d02809dbb..b58dffc58a8f 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1180,13 +1180,15 @@ static int adjust_historical_crosststamp(struct system_time_snapshot *history, } /* - * cycle_between - true if test occurs chronologically between before and after + * timestamp_in_interval - true if ts is chronologically in [start, end] + * + * True if ts occurs chronologically at or after start, and before or at end. */ -static bool cycle_between(u64 before, u64 test, u64 after) +static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { - if (test > before && test < after) + if (ts >= start && ts <= end) return true; - if (test < before && before > after) + if (start > end && (ts >= start || ts <= end)) return true; return false; } @@ -1232,11 +1234,12 @@ int get_device_system_crosststamp(int (*get_time_fn) return ret; /* - * Verify that the clocksource associated with the captured - * system counter value is the same as the currently installed - * timekeeper clocksource + * Verify that the clocksource ID associated with the captured + * system counter value is the same as for the currently + * installed timekeeper clocksource */ - if (tk->tkr_mono.clock != system_counterval.cs) + if (system_counterval.cs_id == CSID_GENERIC || + tk->tkr_mono.clock->id != system_counterval.cs_id) return -ENODEV; cycles = system_counterval.cycles; @@ -1246,7 +1249,7 @@ int get_device_system_crosststamp(int (*get_time_fn) */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; - if (!cycle_between(interval_start, cycles, now)) { + if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; @@ -1259,10 +1262,8 @@ int get_device_system_crosststamp(int (*get_time_fn) tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; - nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, - system_counterval.cycles); - nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, - system_counterval.cycles); + nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); + nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); @@ -1277,13 +1278,13 @@ int get_device_system_crosststamp(int (*get_time_fn) bool discontinuity; /* - * Check that the counter value occurs after the provided + * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || - !cycle_between(history_begin->cycles, - system_counterval.cycles, cycles) || + !timestamp_in_interval(history_begin->cycles, + cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 352b161113cd..e69e75d3858c 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -53,6 +53,7 @@ #include <asm/io.h> #include "tick-internal.h" +#include "timer_migration.h" #define CREATE_TRACE_POINTS #include <trace/events/timer.h> @@ -187,15 +188,66 @@ EXPORT_SYMBOL(jiffies_64); #define WHEEL_SIZE (LVL_SIZE * LVL_DEPTH) #ifdef CONFIG_NO_HZ_COMMON -# define NR_BASES 2 -# define BASE_STD 0 -# define BASE_DEF 1 +/* + * If multiple bases need to be locked, use the base ordering for lock + * nesting, i.e. lowest number first. + */ +# define NR_BASES 3 +# define BASE_LOCAL 0 +# define BASE_GLOBAL 1 +# define BASE_DEF 2 #else # define NR_BASES 1 -# define BASE_STD 0 +# define BASE_LOCAL 0 +# define BASE_GLOBAL 0 # define BASE_DEF 0 #endif +/** + * struct timer_base - Per CPU timer base (number of base depends on config) + * @lock: Lock protecting the timer_base + * @running_timer: When expiring timers, the lock is dropped. To make + * sure not to race agains deleting/modifying a + * currently running timer, the pointer is set to the + * timer, which expires at the moment. If no timer is + * running, the pointer is NULL. + * @expiry_lock: PREEMPT_RT only: Lock is taken in softirq around + * timer expiry callback execution and when trying to + * delete a running timer and it wasn't successful in + * the first glance. It prevents priority inversion + * when callback was preempted on a remote CPU and a + * caller tries to delete the running timer. It also + * prevents a life lock, when the task which tries to + * delete a timer preempted the softirq thread which + * is running the timer callback function. + * @timer_waiters: PREEMPT_RT only: Tells, if there is a waiter + * waiting for the end of the timer callback function + * execution. + * @clk: clock of the timer base; is updated before enqueue + * of a timer; during expiry, it is 1 offset ahead of + * jiffies to avoid endless requeuing to current + * jiffies + * @next_expiry: expiry value of the first timer; it is updated when + * finding the next timer and during enqueue; the + * value is not valid, when next_expiry_recalc is set + * @cpu: Number of CPU the timer base belongs to + * @next_expiry_recalc: States, whether a recalculation of next_expiry is + * required. Value is set true, when a timer was + * deleted. + * @is_idle: Is set, when timer_base is idle. It is triggered by NOHZ + * code. This state is only used in standard + * base. Deferrable timers, which are enqueued remotely + * never wake up an idle CPU. So no matter of supporting it + * for this base. + * @timers_pending: Is set, when a timer is pending in the base. It is only + * reliable when next_expiry_recalc is not set. + * @pending_map: bitmap of the timer wheel; each bit reflects a + * bucket of the wheel. When a bit is set, at least a + * single timer is enqueued in the related bucket. + * @vectors: Array of lists; Each array member reflects a bucket + * of the timer wheel. The list contains all timers + * which are enqueued into a specific bucket. + */ struct timer_base { raw_spinlock_t lock; struct timer_list *running_timer; @@ -583,11 +635,16 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer) /* * We might have to IPI the remote CPU if the base is idle and the - * timer is not deferrable. If the other CPU is on the way to idle - * then it can't set base->is_idle as we hold the base lock: + * timer is pinned. If it is a non pinned timer, it is only queued + * on the remote CPU, when timer was running during queueing. Then + * everything is handled by remote CPU anyway. If the other CPU is + * on the way to idle then it can't set base->is_idle as we hold + * the base lock: */ - if (base->is_idle) + if (base->is_idle) { + WARN_ON_ONCE(!(timer->flags & TIMER_PINNED)); wake_up_nohz_cpu(base->cpu); + } } /* @@ -899,7 +956,10 @@ static int detach_if_pending(struct timer_list *timer, struct timer_base *base, static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) { - struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_STD], cpu); + int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; + struct timer_base *base; + + base = per_cpu_ptr(&timer_bases[index], cpu); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need @@ -912,7 +972,10 @@ static inline struct timer_base *get_timer_cpu_base(u32 tflags, u32 cpu) static inline struct timer_base *get_timer_this_cpu_base(u32 tflags) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + int index = tflags & TIMER_PINNED ? BASE_LOCAL : BASE_GLOBAL; + struct timer_base *base; + + base = this_cpu_ptr(&timer_bases[index]); /* * If the timer is deferrable and NO_HZ_COMMON is set then we need @@ -928,17 +991,6 @@ static inline struct timer_base *get_timer_base(u32 tflags) return get_timer_cpu_base(tflags, tflags & TIMER_CPUMASK); } -static inline struct timer_base * -get_target_base(struct timer_base *base, unsigned tflags) -{ -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) - if (static_branch_likely(&timers_migration_enabled) && - !(tflags & TIMER_PINNED)) - return get_timer_cpu_base(tflags, get_nohz_timer_target()); -#endif - return get_timer_this_cpu_base(tflags); -} - static inline void __forward_timer_base(struct timer_base *base, unsigned long basej) { @@ -1093,7 +1145,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires, unsigned int option if (!ret && (options & MOD_TIMER_PENDING_ONLY)) goto out_unlock; - new_base = get_target_base(base, timer->flags); + new_base = get_timer_this_cpu_base(timer->flags); if (base != new_base) { /* @@ -1246,11 +1298,48 @@ void add_timer(struct timer_list *timer) EXPORT_SYMBOL(add_timer); /** + * add_timer_local() - Start a timer on the local CPU + * @timer: The timer to be started + * + * Same as add_timer() except that the timer flag TIMER_PINNED is set. + * + * See add_timer() for further details. + */ +void add_timer_local(struct timer_list *timer) +{ + if (WARN_ON_ONCE(timer_pending(timer))) + return; + timer->flags |= TIMER_PINNED; + __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); +} +EXPORT_SYMBOL(add_timer_local); + +/** + * add_timer_global() - Start a timer without TIMER_PINNED flag set + * @timer: The timer to be started + * + * Same as add_timer() except that the timer flag TIMER_PINNED is unset. + * + * See add_timer() for further details. + */ +void add_timer_global(struct timer_list *timer) +{ + if (WARN_ON_ONCE(timer_pending(timer))) + return; + timer->flags &= ~TIMER_PINNED; + __mod_timer(timer, timer->expires, MOD_TIMER_NOTPENDING); +} +EXPORT_SYMBOL(add_timer_global); + +/** * add_timer_on - Start a timer on a particular CPU * @timer: The timer to be started * @cpu: The CPU to start it on * - * Same as add_timer() except that it starts the timer on the given CPU. + * Same as add_timer() except that it starts the timer on the given CPU and + * the TIMER_PINNED flag is set. When timer shouldn't be a pinned timer in + * the next round, add_timer_global() should be used instead as it unsets + * the TIMER_PINNED flag. * * See add_timer() for further details. */ @@ -1264,6 +1353,9 @@ void add_timer_on(struct timer_list *timer, int cpu) if (WARN_ON_ONCE(timer_pending(timer))) return; + /* Make sure timer flags have TIMER_PINNED flag set */ + timer->flags |= TIMER_PINNED; + new_base = get_timer_cpu_base(timer->flags, cpu); /* @@ -1911,71 +2003,350 @@ static u64 cmp_next_hrtimer_event(u64 basem, u64 expires) return DIV_ROUND_UP_ULL(nextevt, TICK_NSEC) * TICK_NSEC; } +static unsigned long next_timer_interrupt(struct timer_base *base, + unsigned long basej) +{ + if (base->next_expiry_recalc) + next_expiry_recalc(base); + + /* + * Move next_expiry for the empty base into the future to prevent an + * unnecessary raise of the timer softirq when the next_expiry value + * will be reached even if there is no timer pending. + * + * This update is also required to make timer_base::next_expiry values + * easy comparable to find out which base holds the first pending timer. + */ + if (!base->timers_pending) + base->next_expiry = basej + NEXT_TIMER_MAX_DELTA; + + return base->next_expiry; +} + +static unsigned long fetch_next_timer_interrupt(unsigned long basej, u64 basem, + struct timer_base *base_local, + struct timer_base *base_global, + struct timer_events *tevt) +{ + unsigned long nextevt, nextevt_local, nextevt_global; + bool local_first; + + nextevt_local = next_timer_interrupt(base_local, basej); + nextevt_global = next_timer_interrupt(base_global, basej); + + local_first = time_before_eq(nextevt_local, nextevt_global); + + nextevt = local_first ? nextevt_local : nextevt_global; + + /* + * If the @nextevt is at max. one tick away, use @nextevt and store + * it in the local expiry value. The next global event is irrelevant in + * this case and can be left as KTIME_MAX. + */ + if (time_before_eq(nextevt, basej + 1)) { + /* If we missed a tick already, force 0 delta */ + if (time_before(nextevt, basej)) + nextevt = basej; + tevt->local = basem + (u64)(nextevt - basej) * TICK_NSEC; + + /* + * This is required for the remote check only but it doesn't + * hurt, when it is done for both call sites: + * + * * The remote callers will only take care of the global timers + * as local timers will be handled by CPU itself. When not + * updating tevt->global with the already missed first global + * timer, it is possible that it will be missed completely. + * + * * The local callers will ignore the tevt->global anyway, when + * nextevt is max. one tick away. + */ + if (!local_first) + tevt->global = tevt->local; + return nextevt; + } + + /* + * Update tevt.* values: + * + * If the local queue expires first, then the global event can be + * ignored. If the global queue is empty, nothing to do either. + */ + if (!local_first && base_global->timers_pending) + tevt->global = basem + (u64)(nextevt_global - basej) * TICK_NSEC; + + if (base_local->timers_pending) + tevt->local = basem + (u64)(nextevt_local - basej) * TICK_NSEC; + + return nextevt; +} + +# ifdef CONFIG_SMP /** - * get_next_timer_interrupt - return the time (clock mono) of the next timer + * fetch_next_timer_interrupt_remote() - Store next timers into @tevt * @basej: base time jiffies * @basem: base time clock monotonic + * @tevt: Pointer to the storage for the expiry values + * @cpu: Remote CPU + * + * Stores the next pending local and global timer expiry values in the + * struct pointed to by @tevt. If a queue is empty the corresponding + * field is set to KTIME_MAX. If local event expires before global + * event, global event is set to KTIME_MAX as well. * - * Returns the tick aligned clock monotonic time of the next pending - * timer or KTIME_MAX if no timer is pending. + * Caller needs to make sure timer base locks are held (use + * timer_lock_remote_bases() for this purpose). */ -u64 get_next_timer_interrupt(unsigned long basej, u64 basem) +void fetch_next_timer_interrupt_remote(unsigned long basej, u64 basem, + struct timer_events *tevt, + unsigned int cpu) +{ + struct timer_base *base_local, *base_global; + + /* Preset local / global events */ + tevt->local = tevt->global = KTIME_MAX; + + base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); + base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); + + lockdep_assert_held(&base_local->lock); + lockdep_assert_held(&base_global->lock); + + fetch_next_timer_interrupt(basej, basem, base_local, base_global, tevt); +} + +/** + * timer_unlock_remote_bases - unlock timer bases of cpu + * @cpu: Remote CPU + * + * Unlocks the remote timer bases. + */ +void timer_unlock_remote_bases(unsigned int cpu) + __releases(timer_bases[BASE_LOCAL]->lock) + __releases(timer_bases[BASE_GLOBAL]->lock) +{ + struct timer_base *base_local, *base_global; + + base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); + base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); + + raw_spin_unlock(&base_global->lock); + raw_spin_unlock(&base_local->lock); +} + +/** + * timer_lock_remote_bases - lock timer bases of cpu + * @cpu: Remote CPU + * + * Locks the remote timer bases. + */ +void timer_lock_remote_bases(unsigned int cpu) + __acquires(timer_bases[BASE_LOCAL]->lock) + __acquires(timer_bases[BASE_GLOBAL]->lock) +{ + struct timer_base *base_local, *base_global; + + base_local = per_cpu_ptr(&timer_bases[BASE_LOCAL], cpu); + base_global = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); + + lockdep_assert_irqs_disabled(); + + raw_spin_lock(&base_local->lock); + raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); +} + +/** + * timer_base_is_idle() - Return whether timer base is set idle + * + * Returns value of local timer base is_idle value. + */ +bool timer_base_is_idle(void) +{ + return __this_cpu_read(timer_bases[BASE_LOCAL].is_idle); +} + +static void __run_timer_base(struct timer_base *base); + +/** + * timer_expire_remote() - expire global timers of cpu + * @cpu: Remote CPU + * + * Expire timers of global base of remote CPU. + */ +void timer_expire_remote(unsigned int cpu) +{ + struct timer_base *base = per_cpu_ptr(&timer_bases[BASE_GLOBAL], cpu); + + __run_timer_base(base); +} + +static void timer_use_tmigr(unsigned long basej, u64 basem, + unsigned long *nextevt, bool *tick_stop_path, + bool timer_base_idle, struct timer_events *tevt) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - unsigned long nextevt = basej + NEXT_TIMER_MAX_DELTA; - u64 expires = KTIME_MAX; - bool was_idle; + u64 next_tmigr; + + if (timer_base_idle) + next_tmigr = tmigr_cpu_new_timer(tevt->global); + else if (tick_stop_path) + next_tmigr = tmigr_cpu_deactivate(tevt->global); + else + next_tmigr = tmigr_quick_check(tevt->global); /* - * Pretend that there is no timer pending if the cpu is offline. - * Possible pending timers will be migrated later to an active cpu. + * If the CPU is the last going idle in timer migration hierarchy, make + * sure the CPU will wake up in time to handle remote timers. + * next_tmigr == KTIME_MAX if other CPUs are still active. */ - if (cpu_is_offline(smp_processor_id())) - return expires; + if (next_tmigr < tevt->local) { + u64 tmp; - raw_spin_lock(&base->lock); - if (base->next_expiry_recalc) - next_expiry_recalc(base); + /* If we missed a tick already, force 0 delta */ + if (next_tmigr < basem) + next_tmigr = basem; + + tmp = div_u64(next_tmigr - basem, TICK_NSEC); + + *nextevt = basej + (unsigned long)tmp; + tevt->local = next_tmigr; + } +} +# else +static void timer_use_tmigr(unsigned long basej, u64 basem, + unsigned long *nextevt, bool *tick_stop_path, + bool timer_base_idle, struct timer_events *tevt) +{ + /* + * Make sure first event is written into tevt->local to not miss a + * timer on !SMP systems. + */ + tevt->local = min_t(u64, tevt->local, tevt->global); +} +# endif /* CONFIG_SMP */ + +static inline u64 __get_next_timer_interrupt(unsigned long basej, u64 basem, + bool *idle) +{ + struct timer_events tevt = { .local = KTIME_MAX, .global = KTIME_MAX }; + struct timer_base *base_local, *base_global; + unsigned long nextevt; + bool idle_is_possible; + + /* + * When the CPU is offline, the tick is cancelled and nothing is supposed + * to try to stop it. + */ + if (WARN_ON_ONCE(cpu_is_offline(smp_processor_id()))) { + if (idle) + *idle = true; + return tevt.local; + } + + base_local = this_cpu_ptr(&timer_bases[BASE_LOCAL]); + base_global = this_cpu_ptr(&timer_bases[BASE_GLOBAL]); + + raw_spin_lock(&base_local->lock); + raw_spin_lock_nested(&base_global->lock, SINGLE_DEPTH_NESTING); + + nextevt = fetch_next_timer_interrupt(basej, basem, base_local, + base_global, &tevt); + + /* + * If the next event is only one jiffie ahead there is no need to call + * timer migration hierarchy related functions. The value for the next + * global timer in @tevt struct equals then KTIME_MAX. This is also + * true, when the timer base is idle. + * + * The proper timer migration hierarchy function depends on the callsite + * and whether timer base is idle or not. @nextevt will be updated when + * this CPU needs to handle the first timer migration hierarchy + * event. See timer_use_tmigr() for detailed information. + */ + idle_is_possible = time_after(nextevt, basej + 1); + if (idle_is_possible) + timer_use_tmigr(basej, basem, &nextevt, idle, + base_local->is_idle, &tevt); /* * We have a fresh next event. Check whether we can forward the * base. */ - __forward_timer_base(base, basej); + __forward_timer_base(base_local, basej); + __forward_timer_base(base_global, basej); - if (base->timers_pending) { - nextevt = base->next_expiry; + /* + * Set base->is_idle only when caller is timer_base_try_to_set_idle() + */ + if (idle) { + /* + * Bases are idle if the next event is more than a tick + * away. Caution: @nextevt could have changed by enqueueing a + * global timer into timer migration hierarchy. Therefore a new + * check is required here. + * + * If the base is marked idle then any timer add operation must + * forward the base clk itself to keep granularity small. This + * idle logic is only maintained for the BASE_LOCAL and + * BASE_GLOBAL base, deferrable timers may still see large + * granularity skew (by design). + */ + if (!base_local->is_idle && time_after(nextevt, basej + 1)) { + base_local->is_idle = true; + trace_timer_base_idle(true, base_local->cpu); + } + *idle = base_local->is_idle; - /* If we missed a tick already, force 0 delta */ - if (time_before(nextevt, basej)) - nextevt = basej; - expires = basem + (u64)(nextevt - basej) * TICK_NSEC; - } else { /* - * Move next_expiry for the empty base into the future to - * prevent a unnecessary raise of the timer softirq when the - * next_expiry value will be reached even if there is no timer - * pending. + * When timer base is not set idle, undo the effect of + * tmigr_cpu_deactivate() to prevent inconsitent states - active + * timer base but inactive timer migration hierarchy. + * + * When timer base was already marked idle, nothing will be + * changed here. */ - base->next_expiry = nextevt; + if (!base_local->is_idle && idle_is_possible) + tmigr_cpu_activate(); } - /* - * Base is idle if the next event is more than a tick away. - * - * If the base is marked idle then any timer add operation must forward - * the base clk itself to keep granularity small. This idle logic is - * only maintained for the BASE_STD base, deferrable timers may still - * see large granularity skew (by design). - */ - was_idle = base->is_idle; - base->is_idle = time_after(nextevt, basej + 1); - if (was_idle != base->is_idle) - trace_timer_base_idle(base->is_idle, base->cpu); + raw_spin_unlock(&base_global->lock); + raw_spin_unlock(&base_local->lock); - raw_spin_unlock(&base->lock); + return cmp_next_hrtimer_event(basem, tevt.local); +} - return cmp_next_hrtimer_event(basem, expires); +/** + * get_next_timer_interrupt() - return the time (clock mono) of the next timer + * @basej: base time jiffies + * @basem: base time clock monotonic + * + * Returns the tick aligned clock monotonic time of the next pending timer or + * KTIME_MAX if no timer is pending. If timer of global base was queued into + * timer migration hierarchy, first global timer is not taken into account. If + * it was the last CPU of timer migration hierarchy going idle, first global + * event is taken into account. + */ +u64 get_next_timer_interrupt(unsigned long basej, u64 basem) +{ + return __get_next_timer_interrupt(basej, basem, NULL); +} + +/** + * timer_base_try_to_set_idle() - Try to set the idle state of the timer bases + * @basej: base time jiffies + * @basem: base time clock monotonic + * @idle: pointer to store the value of timer_base->is_idle on return; + * *idle contains the information whether tick was already stopped + * + * Returns the tick aligned clock monotonic time of the next pending timer or + * KTIME_MAX if no timer is pending. When tick was already stopped KTIME_MAX is + * returned as well. + */ +u64 timer_base_try_to_set_idle(unsigned long basej, u64 basem, bool *idle) +{ + if (*idle) + return KTIME_MAX; + + return __get_next_timer_interrupt(basej, basem, idle); } /** @@ -1985,18 +2356,18 @@ u64 get_next_timer_interrupt(unsigned long basej, u64 basem) */ void timer_clear_idle(void) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - /* - * We do this unlocked. The worst outcome is a remote enqueue sending - * a pointless IPI, but taking the lock would just make the window for - * sending the IPI a few instructions smaller for the cost of taking - * the lock in the exit from idle path. + * We do this unlocked. The worst outcome is a remote pinned timer + * enqueue sending a pointless IPI, but taking the lock would just + * make the window for sending the IPI a few instructions smaller + * for the cost of taking the lock in the exit from idle + * path. Required for BASE_LOCAL only. */ - if (base->is_idle) { - base->is_idle = false; - trace_timer_base_idle(false, smp_processor_id()); - } + __this_cpu_write(timer_bases[BASE_LOCAL].is_idle, false); + trace_timer_base_idle(false, smp_processor_id()); + + /* Activate without holding the timer_base->lock */ + tmigr_cpu_activate(); } #endif @@ -2009,11 +2380,10 @@ static inline void __run_timers(struct timer_base *base) struct hlist_head heads[LVL_DEPTH]; int levels; - if (time_before(jiffies, base->next_expiry)) - return; + lockdep_assert_held(&base->lock); - timer_base_lock_expiry(base); - raw_spin_lock_irq(&base->lock); + if (base->running_timer) + return; while (time_after_eq(jiffies, base->clk) && time_after_eq(jiffies, base->next_expiry)) { @@ -2037,20 +2407,40 @@ static inline void __run_timers(struct timer_base *base) while (levels--) expire_timers(base, heads + levels); } +} + +static void __run_timer_base(struct timer_base *base) +{ + if (time_before(jiffies, base->next_expiry)) + return; + + timer_base_lock_expiry(base); + raw_spin_lock_irq(&base->lock); + __run_timers(base); raw_spin_unlock_irq(&base->lock); timer_base_unlock_expiry(base); } +static void run_timer_base(int index) +{ + struct timer_base *base = this_cpu_ptr(&timer_bases[index]); + + __run_timer_base(base); +} + /* * This function runs timers and the timer-tq in bottom half context. */ static __latent_entropy void run_timer_softirq(struct softirq_action *h) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + run_timer_base(BASE_LOCAL); + if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) { + run_timer_base(BASE_GLOBAL); + run_timer_base(BASE_DEF); - __run_timers(base); - if (IS_ENABLED(CONFIG_NO_HZ_COMMON)) - __run_timers(this_cpu_ptr(&timer_bases[BASE_DEF])); + if (is_timers_nohz_active()) + tmigr_handle_remote(); + } } /* @@ -2058,19 +2448,18 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h) */ static void run_local_timers(void) { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_LOCAL]); hrtimer_run_queues(); - /* Raise the softirq only if required. */ - if (time_before(jiffies, base->next_expiry)) { - if (!IS_ENABLED(CONFIG_NO_HZ_COMMON)) - return; - /* CPU is awake, so check the deferrable base. */ - base++; - if (time_before(jiffies, base->next_expiry)) + + for (int i = 0; i < NR_BASES; i++, base++) { + /* Raise the softirq only if required. */ + if (time_after_eq(jiffies, base->next_expiry) || + (i == BASE_DEF && tmigr_requires_handle_remote())) { + raise_softirq(TIMER_SOFTIRQ); return; + } } - raise_softirq(TIMER_SOFTIRQ); } /* diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c index ed7d6ad694fb..1c311c46da50 100644 --- a/kernel/time/timer_list.c +++ b/kernel/time/timer_list.c @@ -147,11 +147,15 @@ static void print_cpu(struct seq_file *m, int cpu, u64 now) # define P_ns(x) \ SEQ_printf(m, " .%-15s: %Lu nsecs\n", #x, \ (unsigned long long)(ktime_to_ns(ts->x))) +# define P_flag(x, f) \ + SEQ_printf(m, " .%-15s: %d\n", #x, !!(ts->flags & (f))) + { struct tick_sched *ts = tick_get_tick_sched(cpu); - P(nohz_mode); + P_flag(nohz, TS_FLAG_NOHZ); + P_flag(highres, TS_FLAG_HIGHRES); P_ns(last_tick); - P(tick_stopped); + P_flag(tick_stopped, TS_FLAG_STOPPED); P(idle_jiffies); P(idle_calls); P(idle_sleeps); @@ -256,7 +260,7 @@ static void timer_list_show_tickdevices_header(struct seq_file *m) static inline void timer_list_header(struct seq_file *m, u64 now) { - SEQ_printf(m, "Timer List Version: v0.9\n"); + SEQ_printf(m, "Timer List Version: v0.10\n"); SEQ_printf(m, "HRTIMER_MAX_CLOCK_BASES: %d\n", HRTIMER_MAX_CLOCK_BASES); SEQ_printf(m, "now at %Ld nsecs\n", (unsigned long long)now); SEQ_printf(m, "\n"); diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c new file mode 100644 index 000000000000..611cd904f035 --- /dev/null +++ b/kernel/time/timer_migration.c @@ -0,0 +1,1773 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Infrastructure for migratable timers + * + * Copyright(C) 2022 linutronix GmbH + */ +#include <linux/cpuhotplug.h> +#include <linux/slab.h> +#include <linux/smp.h> +#include <linux/spinlock.h> +#include <linux/timerqueue.h> +#include <trace/events/ipi.h> + +#include "timer_migration.h" +#include "tick-internal.h" + +#define CREATE_TRACE_POINTS +#include <trace/events/timer_migration.h> + +/* + * The timer migration mechanism is built on a hierarchy of groups. The + * lowest level group contains CPUs, the next level groups of CPU groups + * and so forth. The CPU groups are kept per node so for the normal case + * lock contention won't happen across nodes. Depending on the number of + * CPUs per node even the next level might be kept as groups of CPU groups + * per node and only the levels above cross the node topology. + * + * Example topology for a two node system with 24 CPUs each. + * + * LVL 2 [GRP2:0] + * GRP1:0 = GRP1:M + * + * LVL 1 [GRP1:0] [GRP1:1] + * GRP0:0 - GRP0:2 GRP0:3 - GRP0:5 + * + * LVL 0 [GRP0:0] [GRP0:1] [GRP0:2] [GRP0:3] [GRP0:4] [GRP0:5] + * CPUS 0-7 8-15 16-23 24-31 32-39 40-47 + * + * The groups hold a timer queue of events sorted by expiry time. These + * queues are updated when CPUs go in idle. When they come out of idle + * ignore flag of events is set. + * + * Each group has a designated migrator CPU/group as long as a CPU/group is + * active in the group. This designated role is necessary to avoid that all + * active CPUs in a group try to migrate expired timers from other CPUs, + * which would result in massive lock bouncing. + * + * When a CPU is awake, it checks in it's own timer tick the group + * hierarchy up to the point where it is assigned the migrator role or if + * no CPU is active, it also checks the groups where no migrator is set + * (TMIGR_NONE). + * + * If it finds expired timers in one of the group queues it pulls them over + * from the idle CPU and runs the timer function. After that it updates the + * group and the parent groups if required. + * + * CPUs which go idle arm their CPU local timer hardware for the next local + * (pinned) timer event. If the next migratable timer expires after the + * next local timer or the CPU has no migratable timer pending then the + * CPU does not queue an event in the LVL0 group. If the next migratable + * timer expires before the next local timer then the CPU queues that timer + * in the LVL0 group. In both cases the CPU marks itself idle in the LVL0 + * group. + * + * When CPU comes out of idle and when a group has at least a single active + * child, the ignore flag of the tmigr_event is set. This indicates, that + * the event is ignored even if it is still enqueued in the parent groups + * timer queue. It will be removed when touching the timer queue the next + * time. This spares locking in active path as the lock protects (after + * setup) only event information. For more information about locking, + * please read the section "Locking rules". + * + * If the CPU is the migrator of the group then it delegates that role to + * the next active CPU in the group or sets migrator to TMIGR_NONE when + * there is no active CPU in the group. This delegation needs to be + * propagated up the hierarchy so hand over from other leaves can happen at + * all hierarchy levels w/o doing a search. + * + * When the last CPU in the system goes idle, then it drops all migrator + * duties up to the top level of the hierarchy (LVL2 in the example). It + * then has to make sure, that it arms it's own local hardware timer for + * the earliest event in the system. + * + * + * Lifetime rules: + * --------------- + * + * The groups are built up at init time or when CPUs come online. They are + * not destroyed when a group becomes empty due to offlining. The group + * just won't participate in the hierarchy management anymore. Destroying + * groups would result in interesting race conditions which would just make + * the whole mechanism slow and complex. + * + * + * Locking rules: + * -------------- + * + * For setting up new groups and handling events it's required to lock both + * child and parent group. The lock ordering is always bottom up. This also + * includes the per CPU locks in struct tmigr_cpu. For updating the migrator and + * active CPU/group information atomic_try_cmpxchg() is used instead and only + * the per CPU tmigr_cpu->lock is held. + * + * During the setup of groups tmigr_level_list is required. It is protected by + * @tmigr_mutex. + * + * When @timer_base->lock as well as tmigr related locks are required, the lock + * ordering is: first @timer_base->lock, afterwards tmigr related locks. + * + * + * Protection of the tmigr group state information: + * ------------------------------------------------ + * + * The state information with the list of active children and migrator needs to + * be protected by a sequence counter. It prevents a race when updates in child + * groups are propagated in changed order. The state update is performed + * lockless and group wise. The following scenario describes what happens + * without updating the sequence counter: + * + * Therefore, let's take three groups and four CPUs (CPU2 and CPU3 as well + * as GRP0:1 will not change during the scenario): + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:0, GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = CPU0 migrator = CPU2 + * active = CPU0 active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * active idle active idle + * + * + * 1. CPU0 goes idle. As the update is performed group wise, in the first step + * only GRP0:0 is updated. The update of GRP1:0 is pending as CPU0 has to + * walk the hierarchy. + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:0, GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * --> migrator = TMIGR_NONE migrator = CPU2 + * --> active = active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * --> idle idle active idle + * + * 2. While CPU0 goes idle and continues to update the state, CPU1 comes out of + * idle. CPU1 updates GRP0:0. The update for GRP1:0 is pending as CPU1 also + * has to walk the hierarchy. Both CPUs (CPU0 and CPU1) now walk the + * hierarchy to perform the needed update from their point of view. The + * currently visible state looks the following: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:0, GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * --> migrator = CPU1 migrator = CPU2 + * --> active = CPU1 active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * idle --> active active idle + * + * 3. Here is the race condition: CPU1 managed to propagate its changes (from + * step 2) through the hierarchy to GRP1:0 before CPU0 (step 1) did. The + * active members of GRP1:0 remain unchanged after the update since it is + * still valid from CPU1 current point of view: + * + * LVL 1 [GRP1:0] + * --> migrator = GRP0:1 + * --> active = GRP0:0, GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = CPU1 migrator = CPU2 + * active = CPU1 active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * idle active active idle + * + * 4. Now CPU0 finally propagates its changes (from step 1) to GRP1:0. + * + * LVL 1 [GRP1:0] + * --> migrator = GRP0:1 + * --> active = GRP0:1 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = CPU1 migrator = CPU2 + * active = CPU1 active = CPU2 + * / \ / \ + * CPUs 0 1 2 3 + * idle active active idle + * + * + * The race of CPU0 vs. CPU1 led to an inconsistent state in GRP1:0. CPU1 is + * active and is correctly listed as active in GRP0:0. However GRP1:0 does not + * have GRP0:0 listed as active, which is wrong. The sequence counter has been + * added to avoid inconsistent states during updates. The state is updated + * atomically only if all members, including the sequence counter, match the + * expected value (compare-and-exchange). + * + * Looking back at the previous example with the addition of the sequence + * counter: The update as performed by CPU0 in step 4 will fail. CPU1 changed + * the sequence number during the update in step 3 so the expected old value (as + * seen by CPU0 before starting the walk) does not match. + * + * Prevent race between new event and last CPU going inactive + * ---------------------------------------------------------- + * + * When the last CPU is going idle and there is a concurrent update of a new + * first global timer of an idle CPU, the group and child states have to be read + * while holding the lock in tmigr_update_events(). The following scenario shows + * what happens, when this is not done. + * + * 1. Only CPU2 is active: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * next_expiry = KTIME_MAX + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = CPU2 + * active = active = CPU2 + * next_expiry = KTIME_MAX next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle active idle + * + * 2. Now CPU 2 goes idle (and has no global timer, that has to be handled) and + * propagates that to GRP0:1: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * next_expiry = KTIME_MAX + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE --> migrator = TMIGR_NONE + * active = --> active = + * next_expiry = KTIME_MAX next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle --> idle idle + * + * 3. Now the idle state is propagated up to GRP1:0. As this is now the last + * child going idle in top level group, the expiry of the next group event + * has to be handed back to make sure no event is lost. As there is no event + * enqueued, KTIME_MAX is handed back to CPU2. + * + * LVL 1 [GRP1:0] + * --> migrator = TMIGR_NONE + * --> active = + * next_expiry = KTIME_MAX + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = TMIGR_NONE + * active = active = + * next_expiry = KTIME_MAX next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle --> idle idle + * + * 4. CPU 0 has a new timer queued from idle and it expires at TIMER0. CPU0 + * propagates that to GRP0:0: + * + * LVL 1 [GRP1:0] + * migrator = TMIGR_NONE + * active = + * next_expiry = KTIME_MAX + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = TMIGR_NONE + * active = active = + * --> next_expiry = TIMER0 next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle idle idle + * + * 5. GRP0:0 is not active, so the new timer has to be propagated to + * GRP1:0. Therefore the GRP1:0 state has to be read. When the stalled value + * (from step 2) is read, the timer is enqueued into GRP1:0, but nothing is + * handed back to CPU0, as it seems that there is still an active child in + * top level group. + * + * LVL 1 [GRP1:0] + * migrator = TMIGR_NONE + * active = + * --> next_expiry = TIMER0 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = TMIGR_NONE + * active = active = + * next_expiry = TIMER0 next_expiry = KTIME_MAX + * / \ / \ + * CPUs 0 1 2 3 + * idle idle idle idle + * + * This is prevented by reading the state when holding the lock (when a new + * timer has to be propagated from idle path):: + * + * CPU2 (tmigr_inactive_up()) CPU0 (tmigr_new_timer_up()) + * -------------------------- --------------------------- + * // step 3: + * cmpxchg(&GRP1:0->state); + * tmigr_update_events() { + * spin_lock(&GRP1:0->lock); + * // ... update events ... + * // hand back first expiry when GRP1:0 is idle + * spin_unlock(&GRP1:0->lock); + * // ^^^ release state modification + * } + * tmigr_update_events() { + * spin_lock(&GRP1:0->lock) + * // ^^^ acquire state modification + * group_state = atomic_read(&GRP1:0->state) + * // .... update events ... + * // hand back first expiry when GRP1:0 is idle + * spin_unlock(&GRP1:0->lock) <3> + * // ^^^ makes state visible for other + * // callers of tmigr_new_timer_up() + * } + * + * When CPU0 grabs the lock directly after cmpxchg, the first timer is reported + * back to CPU0 and also later on to CPU2. So no timer is missed. A concurrent + * update of the group state from active path is no problem, as the upcoming CPU + * will take care of the group events. + * + * Required event and timerqueue update after a remote expiry: + * ----------------------------------------------------------- + * + * After expiring timers of a remote CPU, a walk through the hierarchy and + * update of events and timerqueues is required. It is obviously needed if there + * is a 'new' global timer but also if there is no new global timer but the + * remote CPU is still idle. + * + * 1. CPU0 and CPU1 are idle and have both a global timer expiring at the same + * time. So both have an event enqueued in the timerqueue of GRP0:0. CPU3 is + * also idle and has no global timer pending. CPU2 is the only active CPU and + * thus also the migrator: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * --> timerqueue = evt-GRP0:0 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = CPU2 + * active = active = CPU2 + * groupevt.ignore = false groupevt.ignore = true + * groupevt.cpu = CPU0 groupevt.cpu = + * timerqueue = evt-CPU0, timerqueue = + * evt-CPU1 + * / \ / \ + * CPUs 0 1 2 3 + * idle idle active idle + * + * 2. CPU2 starts to expire remote timers. It starts with LVL0 group + * GRP0:1. There is no event queued in the timerqueue, so CPU2 continues with + * the parent of GRP0:1: GRP1:0. In GRP1:0 it dequeues the first event. It + * looks at tmigr_event::cpu struct member and expires the pending timer(s) + * of CPU0. + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * --> timerqueue = + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = CPU2 + * active = active = CPU2 + * groupevt.ignore = false groupevt.ignore = true + * --> groupevt.cpu = CPU0 groupevt.cpu = + * timerqueue = evt-CPU0, timerqueue = + * evt-CPU1 + * / \ / \ + * CPUs 0 1 2 3 + * idle idle active idle + * + * 3. Some work has to be done after expiring the timers of CPU0. If we stop + * here, then CPU1's pending global timer(s) will not expire in time and the + * timerqueue of GRP0:0 has still an event for CPU0 enqueued which has just + * been processed. So it is required to walk the hierarchy from CPU0's point + * of view and update it accordingly. CPU0's event will be removed from the + * timerqueue because it has no pending timer. If CPU0 would have a timer + * pending then it has to expire after CPU1's first timer because all timers + * from this period were just expired. Either way CPU1's event will be first + * in GRP0:0's timerqueue and therefore set in the CPU field of the group + * event which is then enqueued in GRP1:0's timerqueue as GRP0:0 is still not + * active: + * + * LVL 1 [GRP1:0] + * migrator = GRP0:1 + * active = GRP0:1 + * --> timerqueue = evt-GRP0:0 + * / \ + * LVL 0 [GRP0:0] [GRP0:1] + * migrator = TMIGR_NONE migrator = CPU2 + * active = active = CPU2 + * groupevt.ignore = false groupevt.ignore = true + * --> groupevt.cpu = CPU1 groupevt.cpu = + * --> timerqueue = evt-CPU1 timerqueue = + * / \ / \ + * CPUs 0 1 2 3 + * idle idle active idle + * + * Now CPU2 (migrator) will continue step 2 at GRP1:0 and will expire the + * timer(s) of CPU1. + * + * The hierarchy walk in step 3 can be skipped if the migrator notices that a + * CPU of GRP0:0 is active again. The CPU will mark GRP0:0 active and take care + * of the group as migrator and any needed updates within the hierarchy. + */ + +static DEFINE_MUTEX(tmigr_mutex); +static struct list_head *tmigr_level_list __read_mostly; + +static unsigned int tmigr_hierarchy_levels __read_mostly; +static unsigned int tmigr_crossnode_level __read_mostly; + +static DEFINE_PER_CPU(struct tmigr_cpu, tmigr_cpu); + +#define TMIGR_NONE 0xFF +#define BIT_CNT 8 + +static inline bool tmigr_is_not_available(struct tmigr_cpu *tmc) +{ + return !(tmc->tmgroup && tmc->online); +} + +/* + * Returns true, when @childmask corresponds to the group migrator or when the + * group is not active - so no migrator is set. + */ +static bool tmigr_check_migrator(struct tmigr_group *group, u8 childmask) +{ + union tmigr_state s; + + s.state = atomic_read(&group->migr_state); + + if ((s.migrator == childmask) || (s.migrator == TMIGR_NONE)) + return true; + + return false; +} + +static bool tmigr_check_migrator_and_lonely(struct tmigr_group *group, u8 childmask) +{ + bool lonely, migrator = false; + unsigned long active; + union tmigr_state s; + + s.state = atomic_read(&group->migr_state); + + if ((s.migrator == childmask) || (s.migrator == TMIGR_NONE)) + migrator = true; + + active = s.active; + lonely = bitmap_weight(&active, BIT_CNT) <= 1; + + return (migrator && lonely); +} + +static bool tmigr_check_lonely(struct tmigr_group *group) +{ + unsigned long active; + union tmigr_state s; + + s.state = atomic_read(&group->migr_state); + + active = s.active; + + return bitmap_weight(&active, BIT_CNT) <= 1; +} + +typedef bool (*up_f)(struct tmigr_group *, struct tmigr_group *, void *); + +static void __walk_groups(up_f up, void *data, + struct tmigr_cpu *tmc) +{ + struct tmigr_group *child = NULL, *group = tmc->tmgroup; + + do { + WARN_ON_ONCE(group->level >= tmigr_hierarchy_levels); + + if (up(group, child, data)) + break; + + child = group; + group = group->parent; + } while (group); +} + +static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc) +{ + lockdep_assert_held(&tmc->lock); + + __walk_groups(up, data, tmc); +} + +/** + * struct tmigr_walk - data required for walking the hierarchy + * @nextexp: Next CPU event expiry information which is handed into + * the timer migration code by the timer code + * (get_next_timer_interrupt()) + * @firstexp: Contains the first event expiry information when last + * active CPU of hierarchy is on the way to idle to make + * sure CPU will be back in time. + * @evt: Pointer to tmigr_event which needs to be queued (of idle + * child group) + * @childmask: childmask of child group + * @remote: Is set, when the new timer path is executed in + * tmigr_handle_remote_cpu() + */ +struct tmigr_walk { + u64 nextexp; + u64 firstexp; + struct tmigr_event *evt; + u8 childmask; + bool remote; +}; + +/** + * struct tmigr_remote_data - data required for remote expiry hierarchy walk + * @basej: timer base in jiffies + * @now: timer base monotonic + * @firstexp: returns expiry of the first timer in the idle timer + * migration hierarchy to make sure the timer is handled in + * time; it is stored in the per CPU tmigr_cpu struct of + * CPU which expires remote timers + * @childmask: childmask of child group + * @check: is set if there is the need to handle remote timers; + * required in tmigr_requires_handle_remote() only + * @tmc_active: this flag indicates, whether the CPU which triggers + * the hierarchy walk is !idle in the timer migration + * hierarchy. When the CPU is idle and the whole hierarchy is + * idle, only the first event of the top level has to be + * considered. + */ +struct tmigr_remote_data { + unsigned long basej; + u64 now; + u64 firstexp; + u8 childmask; + bool check; + bool tmc_active; +}; + +/* + * Returns the next event of the timerqueue @group->events + * + * Removes timers with ignore flag and update next_expiry of the group. Values + * of the group event are updated in tmigr_update_events() only. + */ +static struct tmigr_event *tmigr_next_groupevt(struct tmigr_group *group) +{ + struct timerqueue_node *node = NULL; + struct tmigr_event *evt = NULL; + + lockdep_assert_held(&group->lock); + + WRITE_ONCE(group->next_expiry, KTIME_MAX); + + while ((node = timerqueue_getnext(&group->events))) { + evt = container_of(node, struct tmigr_event, nextevt); + + if (!evt->ignore) { + WRITE_ONCE(group->next_expiry, evt->nextevt.expires); + return evt; + } + + /* + * Remove next timers with ignore flag, because the group lock + * is held anyway + */ + if (!timerqueue_del(&group->events, node)) + break; + } + + return NULL; +} + +/* + * Return the next event (with the expiry equal or before @now) + * + * Event, which is returned, is also removed from the queue. + */ +static struct tmigr_event *tmigr_next_expired_groupevt(struct tmigr_group *group, + u64 now) +{ + struct tmigr_event *evt = tmigr_next_groupevt(group); + + if (!evt || now < evt->nextevt.expires) + return NULL; + + /* + * The event is ready to expire. Remove it and update next group event. + */ + timerqueue_del(&group->events, &evt->nextevt); + tmigr_next_groupevt(group); + + return evt; +} + +static u64 tmigr_next_groupevt_expires(struct tmigr_group *group) +{ + struct tmigr_event *evt; + + evt = tmigr_next_groupevt(group); + + if (!evt) + return KTIME_MAX; + else + return evt->nextevt.expires; +} + +static bool tmigr_active_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + union tmigr_state curstate, newstate; + struct tmigr_walk *data = ptr; + bool walk_done; + u8 childmask; + + childmask = data->childmask; + /* + * No memory barrier is required here in contrast to + * tmigr_inactive_up(), as the group state change does not depend on the + * child state. + */ + curstate.state = atomic_read(&group->migr_state); + + do { + newstate = curstate; + walk_done = true; + + if (newstate.migrator == TMIGR_NONE) { + newstate.migrator = childmask; + + /* Changes need to be propagated */ + walk_done = false; + } + + newstate.active |= childmask; + newstate.seq++; + + } while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state)); + + if ((walk_done == false) && group->parent) + data->childmask = group->childmask; + + /* + * The group is active (again). The group event might be still queued + * into the parent group's timerqueue but can now be handled by the + * migrator of this group. Therefore the ignore flag for the group event + * is updated to reflect this. + * + * The update of the ignore flag in the active path is done lockless. In + * worst case the migrator of the parent group observes the change too + * late and expires remotely all events belonging to this group. The + * lock is held while updating the ignore flag in idle path. So this + * state change will not be lost. + */ + group->groupevt.ignore = true; + + trace_tmigr_group_set_cpu_active(group, newstate, childmask); + + return walk_done; +} + +static void __tmigr_cpu_activate(struct tmigr_cpu *tmc) +{ + struct tmigr_walk data; + + data.childmask = tmc->childmask; + + trace_tmigr_cpu_active(tmc); + + tmc->cpuevt.ignore = true; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + + walk_groups(&tmigr_active_up, &data, tmc); +} + +/** + * tmigr_cpu_activate() - set this CPU active in timer migration hierarchy + * + * Call site timer_clear_idle() is called with interrupts disabled. + */ +void tmigr_cpu_activate(void) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + if (tmigr_is_not_available(tmc)) + return; + + if (WARN_ON_ONCE(!tmc->idle)) + return; + + raw_spin_lock(&tmc->lock); + tmc->idle = false; + __tmigr_cpu_activate(tmc); + raw_spin_unlock(&tmc->lock); +} + +/* + * Returns true, if there is nothing to be propagated to the next level + * + * @data->firstexp is set to expiry of first gobal event of the (top level of + * the) hierarchy, but only when hierarchy is completely idle. + * + * The child and group states need to be read under the lock, to prevent a race + * against a concurrent tmigr_inactive_up() run when the last CPU goes idle. See + * also section "Prevent race between new event and last CPU going inactive" in + * the documentation at the top. + * + * This is the only place where the group event expiry value is set. + */ +static +bool tmigr_update_events(struct tmigr_group *group, struct tmigr_group *child, + struct tmigr_walk *data) +{ + struct tmigr_event *evt, *first_childevt; + union tmigr_state childstate, groupstate; + bool remote = data->remote; + bool walk_done = false; + u64 nextexp; + + if (child) { + raw_spin_lock(&child->lock); + raw_spin_lock_nested(&group->lock, SINGLE_DEPTH_NESTING); + + childstate.state = atomic_read(&child->migr_state); + groupstate.state = atomic_read(&group->migr_state); + + if (childstate.active) { + walk_done = true; + goto unlock; + } + + first_childevt = tmigr_next_groupevt(child); + nextexp = child->next_expiry; + evt = &child->groupevt; + + evt->ignore = (nextexp == KTIME_MAX) ? true : false; + } else { + nextexp = data->nextexp; + + first_childevt = evt = data->evt; + + raw_spin_lock(&group->lock); + + childstate.state = 0; + groupstate.state = atomic_read(&group->migr_state); + } + + /* + * If the child event is already queued in the group, remove it from the + * queue when the expiry time changed only or when it could be ignored. + */ + if (timerqueue_node_queued(&evt->nextevt)) { + if ((evt->nextevt.expires == nextexp) && !evt->ignore) + goto check_toplvl; + + if (!timerqueue_del(&group->events, &evt->nextevt)) + WRITE_ONCE(group->next_expiry, KTIME_MAX); + } + + if (evt->ignore) { + /* + * When the next child event could be ignored (nextexp is + * KTIME_MAX) and there was no remote timer handling before or + * the group is already active, there is no need to walk the + * hierarchy even if there is a parent group. + * + * The other way round: even if the event could be ignored, but + * if a remote timer handling was executed before and the group + * is not active, walking the hierarchy is required to not miss + * an enqueued timer in the non active group. The enqueued timer + * of the group needs to be propagated to a higher level to + * ensure it is handled. + */ + if (!remote || groupstate.active) + walk_done = true; + } else { + evt->nextevt.expires = nextexp; + evt->cpu = first_childevt->cpu; + + if (timerqueue_add(&group->events, &evt->nextevt)) + WRITE_ONCE(group->next_expiry, nextexp); + } + +check_toplvl: + if (!group->parent && (groupstate.migrator == TMIGR_NONE)) { + walk_done = true; + + /* + * Nothing to do when update was done during remote timer + * handling. First timer in top level group which needs to be + * handled when top level group is not active, is calculated + * directly in tmigr_handle_remote_up(). + */ + if (remote) + goto unlock; + + /* + * The top level group is idle and it has to be ensured the + * global timers are handled in time. (This could be optimized + * by keeping track of the last global scheduled event and only + * arming it on the CPU if the new event is earlier. Not sure if + * its worth the complexity.) + */ + data->firstexp = tmigr_next_groupevt_expires(group); + } + + trace_tmigr_update_events(child, group, childstate, groupstate, + nextexp); + +unlock: + raw_spin_unlock(&group->lock); + + if (child) + raw_spin_unlock(&child->lock); + + return walk_done; +} + +static bool tmigr_new_timer_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + struct tmigr_walk *data = ptr; + + return tmigr_update_events(group, child, data); +} + +/* + * Returns the expiry of the next timer that needs to be handled. KTIME_MAX is + * returned, if an active CPU will handle all the timer migration hierarchy + * timers. + */ +static u64 tmigr_new_timer(struct tmigr_cpu *tmc, u64 nextexp) +{ + struct tmigr_walk data = { .nextexp = nextexp, + .firstexp = KTIME_MAX, + .evt = &tmc->cpuevt }; + + lockdep_assert_held(&tmc->lock); + + if (tmc->remote) + return KTIME_MAX; + + trace_tmigr_cpu_new_timer(tmc); + + tmc->cpuevt.ignore = false; + data.remote = false; + + walk_groups(&tmigr_new_timer_up, &data, tmc); + + /* If there is a new first global event, make sure it is handled */ + return data.firstexp; +} + +static void tmigr_handle_remote_cpu(unsigned int cpu, u64 now, + unsigned long jif) +{ + struct timer_events tevt; + struct tmigr_walk data; + struct tmigr_cpu *tmc; + + tmc = per_cpu_ptr(&tmigr_cpu, cpu); + + raw_spin_lock_irq(&tmc->lock); + + /* + * If the remote CPU is offline then the timers have been migrated to + * another CPU. + * + * If tmigr_cpu::remote is set, at the moment another CPU already + * expires the timers of the remote CPU. + * + * If tmigr_event::ignore is set, then the CPU returns from idle and + * takes care of its timers. + * + * If the next event expires in the future, then the event has been + * updated and there are no timers to expire right now. The CPU which + * updated the event takes care when hierarchy is completely + * idle. Otherwise the migrator does it as the event is enqueued. + */ + if (!tmc->online || tmc->remote || tmc->cpuevt.ignore || + now < tmc->cpuevt.nextevt.expires) { + raw_spin_unlock_irq(&tmc->lock); + return; + } + + trace_tmigr_handle_remote_cpu(tmc); + + tmc->remote = true; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + + /* Drop the lock to allow the remote CPU to exit idle */ + raw_spin_unlock_irq(&tmc->lock); + + if (cpu != smp_processor_id()) + timer_expire_remote(cpu); + + /* + * Lock ordering needs to be preserved - timer_base locks before tmigr + * related locks (see section "Locking rules" in the documentation at + * the top). During fetching the next timer interrupt, also tmc->lock + * needs to be held. Otherwise there is a possible race window against + * the CPU itself when it comes out of idle, updates the first timer in + * the hierarchy and goes back to idle. + * + * timer base locks are dropped as fast as possible: After checking + * whether the remote CPU went offline in the meantime and after + * fetching the next remote timer interrupt. Dropping the locks as fast + * as possible keeps the locking region small and prevents holding + * several (unnecessary) locks during walking the hierarchy for updating + * the timerqueue and group events. + */ + local_irq_disable(); + timer_lock_remote_bases(cpu); + raw_spin_lock(&tmc->lock); + + /* + * When the CPU went offline in the meantime, no hierarchy walk has to + * be done for updating the queued events, because the walk was + * already done during marking the CPU offline in the hierarchy. + * + * When the CPU is no longer idle, the CPU takes care of the timers and + * also of the timers in the hierarchy. + * + * (See also section "Required event and timerqueue update after a + * remote expiry" in the documentation at the top) + */ + if (!tmc->online || !tmc->idle) { + timer_unlock_remote_bases(cpu); + goto unlock; + } + + /* next event of CPU */ + fetch_next_timer_interrupt_remote(jif, now, &tevt, cpu); + timer_unlock_remote_bases(cpu); + + data.nextexp = tevt.global; + data.firstexp = KTIME_MAX; + data.evt = &tmc->cpuevt; + data.remote = true; + + /* + * The update is done even when there is no 'new' global timer pending + * on the remote CPU (see section "Required event and timerqueue update + * after a remote expiry" in the documentation at the top) + */ + walk_groups(&tmigr_new_timer_up, &data, tmc); + +unlock: + tmc->remote = false; + raw_spin_unlock_irq(&tmc->lock); +} + +static bool tmigr_handle_remote_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + struct tmigr_remote_data *data = ptr; + struct tmigr_event *evt; + unsigned long jif; + u8 childmask; + u64 now; + + jif = data->basej; + now = data->now; + + childmask = data->childmask; + + trace_tmigr_handle_remote(group); +again: + /* + * Handle the group only if @childmask is the migrator or if the + * group has no migrator. Otherwise the group is active and is + * handled by its own migrator. + */ + if (!tmigr_check_migrator(group, childmask)) + return true; + + raw_spin_lock_irq(&group->lock); + + evt = tmigr_next_expired_groupevt(group, now); + + if (evt) { + unsigned int remote_cpu = evt->cpu; + + raw_spin_unlock_irq(&group->lock); + + tmigr_handle_remote_cpu(remote_cpu, now, jif); + + /* check if there is another event, that needs to be handled */ + goto again; + } + + /* + * Update of childmask for the next level and keep track of the expiry + * of the first event that needs to be handled (group->next_expiry was + * updated by tmigr_next_expired_groupevt(), next was set by + * tmigr_handle_remote_cpu()). + */ + data->childmask = group->childmask; + data->firstexp = group->next_expiry; + + raw_spin_unlock_irq(&group->lock); + + return false; +} + +/** + * tmigr_handle_remote() - Handle global timers of remote idle CPUs + * + * Called from the timer soft interrupt with interrupts enabled. + */ +void tmigr_handle_remote(void) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_remote_data data; + + if (tmigr_is_not_available(tmc)) + return; + + data.childmask = tmc->childmask; + data.firstexp = KTIME_MAX; + + /* + * NOTE: This is a doubled check because the migrator test will be done + * in tmigr_handle_remote_up() anyway. Keep this check to speed up the + * return when nothing has to be done. + */ + if (!tmigr_check_migrator(tmc->tmgroup, tmc->childmask)) + return; + + data.now = get_jiffies_update(&data.basej); + + /* + * Update @tmc->wakeup only at the end and do not reset @tmc->wakeup to + * KTIME_MAX. Even if tmc->lock is not held during the whole remote + * handling, tmc->wakeup is fine to be stale as it is called in + * interrupt context and tick_nohz_next_event() is executed in interrupt + * exit path only after processing the last pending interrupt. + */ + + __walk_groups(&tmigr_handle_remote_up, &data, tmc); + + raw_spin_lock_irq(&tmc->lock); + WRITE_ONCE(tmc->wakeup, data.firstexp); + raw_spin_unlock_irq(&tmc->lock); +} + +static bool tmigr_requires_handle_remote_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + struct tmigr_remote_data *data = ptr; + u8 childmask; + + childmask = data->childmask; + + /* + * Handle the group only if the child is the migrator or if the group + * has no migrator. Otherwise the group is active and is handled by its + * own migrator. + */ + if (!tmigr_check_migrator(group, childmask)) + return true; + + /* + * When there is a parent group and the CPU which triggered the + * hierarchy walk is not active, proceed the walk to reach the top level + * group before reading the next_expiry value. + */ + if (group->parent && !data->tmc_active) + goto out; + + /* + * The lock is required on 32bit architectures to read the variable + * consistently with a concurrent writer. On 64bit the lock is not + * required because the read operation is not split and so it is always + * consistent. + */ + if (IS_ENABLED(CONFIG_64BIT)) { + data->firstexp = READ_ONCE(group->next_expiry); + if (data->now >= data->firstexp) { + data->check = true; + return true; + } + } else { + raw_spin_lock(&group->lock); + data->firstexp = group->next_expiry; + if (data->now >= group->next_expiry) { + data->check = true; + raw_spin_unlock(&group->lock); + return true; + } + raw_spin_unlock(&group->lock); + } + +out: + /* Update of childmask for the next level */ + data->childmask = group->childmask; + return false; +} + +/** + * tmigr_requires_handle_remote() - Check the need of remote timer handling + * + * Must be called with interrupts disabled. + */ +bool tmigr_requires_handle_remote(void) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_remote_data data; + unsigned long jif; + bool ret = false; + + if (tmigr_is_not_available(tmc)) + return ret; + + data.now = get_jiffies_update(&jif); + data.childmask = tmc->childmask; + data.firstexp = KTIME_MAX; + data.tmc_active = !tmc->idle; + data.check = false; + + /* + * If the CPU is active, walk the hierarchy to check whether a remote + * expiry is required. + * + * Check is done lockless as interrupts are disabled and @tmc->idle is + * set only by the local CPU. + */ + if (!tmc->idle) { + __walk_groups(&tmigr_requires_handle_remote_up, &data, tmc); + + return data.check; + } + + /* + * When the CPU is idle, compare @tmc->wakeup with @data.now. The lock + * is required on 32bit architectures to read the variable consistently + * with a concurrent writer. On 64bit the lock is not required because + * the read operation is not split and so it is always consistent. + */ + if (IS_ENABLED(CONFIG_64BIT)) { + if (data.now >= READ_ONCE(tmc->wakeup)) + return true; + } else { + raw_spin_lock(&tmc->lock); + if (data.now >= tmc->wakeup) + ret = true; + raw_spin_unlock(&tmc->lock); + } + + return ret; +} + +/** + * tmigr_cpu_new_timer() - enqueue next global timer into hierarchy (idle tmc) + * @nextexp: Next expiry of global timer (or KTIME_MAX if not) + * + * The CPU is already deactivated in the timer migration + * hierarchy. tick_nohz_get_sleep_length() calls tick_nohz_next_event() + * and thereby the timer idle path is executed once more. @tmc->wakeup + * holds the first timer, when the timer migration hierarchy is + * completely idle. + * + * Returns the first timer that needs to be handled by this CPU or KTIME_MAX if + * nothing needs to be done. + */ +u64 tmigr_cpu_new_timer(u64 nextexp) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + u64 ret; + + if (tmigr_is_not_available(tmc)) + return nextexp; + + raw_spin_lock(&tmc->lock); + + ret = READ_ONCE(tmc->wakeup); + if (nextexp != KTIME_MAX) { + if (nextexp != tmc->cpuevt.nextevt.expires || + tmc->cpuevt.ignore) { + ret = tmigr_new_timer(tmc, nextexp); + } + } + /* + * Make sure the reevaluation of timers in idle path will not miss an + * event. + */ + WRITE_ONCE(tmc->wakeup, ret); + + trace_tmigr_cpu_new_timer_idle(tmc, nextexp); + raw_spin_unlock(&tmc->lock); + return ret; +} + +static bool tmigr_inactive_up(struct tmigr_group *group, + struct tmigr_group *child, + void *ptr) +{ + union tmigr_state curstate, newstate, childstate; + struct tmigr_walk *data = ptr; + bool walk_done; + u8 childmask; + + childmask = data->childmask; + childstate.state = 0; + + /* + * The memory barrier is paired with the cmpxchg() in tmigr_active_up() + * to make sure the updates of child and group states are ordered. The + * ordering is mandatory, as the group state change depends on the child + * state. + */ + curstate.state = atomic_read_acquire(&group->migr_state); + + for (;;) { + if (child) + childstate.state = atomic_read(&child->migr_state); + + newstate = curstate; + walk_done = true; + + /* Reset active bit when the child is no longer active */ + if (!childstate.active) + newstate.active &= ~childmask; + + if (newstate.migrator == childmask) { + /* + * Find a new migrator for the group, because the child + * group is idle! + */ + if (!childstate.active) { + unsigned long new_migr_bit, active = newstate.active; + + new_migr_bit = find_first_bit(&active, BIT_CNT); + + if (new_migr_bit != BIT_CNT) { + newstate.migrator = BIT(new_migr_bit); + } else { + newstate.migrator = TMIGR_NONE; + + /* Changes need to be propagated */ + walk_done = false; + } + } + } + + newstate.seq++; + + WARN_ON_ONCE((newstate.migrator != TMIGR_NONE) && !(newstate.active)); + + if (atomic_try_cmpxchg(&group->migr_state, &curstate.state, + newstate.state)) + break; + + /* + * The memory barrier is paired with the cmpxchg() in + * tmigr_active_up() to make sure the updates of child and group + * states are ordered. It is required only when the above + * try_cmpxchg() fails. + */ + smp_mb__after_atomic(); + } + + data->remote = false; + + /* Event Handling */ + tmigr_update_events(group, child, data); + + if (group->parent && (walk_done == false)) + data->childmask = group->childmask; + + /* + * data->firstexp was set by tmigr_update_events() and contains the + * expiry of the first global event which needs to be handled. It + * differs from KTIME_MAX if: + * - group is the top level group and + * - group is idle (which means CPU was the last active CPU in the + * hierarchy) and + * - there is a pending event in the hierarchy + */ + WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent); + + trace_tmigr_group_set_cpu_inactive(group, newstate, childmask); + + return walk_done; +} + +static u64 __tmigr_cpu_deactivate(struct tmigr_cpu *tmc, u64 nextexp) +{ + struct tmigr_walk data = { .nextexp = nextexp, + .firstexp = KTIME_MAX, + .evt = &tmc->cpuevt, + .childmask = tmc->childmask }; + + /* + * If nextexp is KTIME_MAX, the CPU event will be ignored because the + * local timer expires before the global timer, no global timer is set + * or CPU goes offline. + */ + if (nextexp != KTIME_MAX) + tmc->cpuevt.ignore = false; + + walk_groups(&tmigr_inactive_up, &data, tmc); + return data.firstexp; +} + +/** + * tmigr_cpu_deactivate() - Put current CPU into inactive state + * @nextexp: The next global timer expiry of the current CPU + * + * Must be called with interrupts disabled. + * + * Return: the next event expiry of the current CPU or the next event expiry + * from the hierarchy if this CPU is the top level migrator or the hierarchy is + * completely idle. + */ +u64 tmigr_cpu_deactivate(u64 nextexp) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + u64 ret; + + if (tmigr_is_not_available(tmc)) + return nextexp; + + raw_spin_lock(&tmc->lock); + + ret = __tmigr_cpu_deactivate(tmc, nextexp); + + tmc->idle = true; + + /* + * Make sure the reevaluation of timers in idle path will not miss an + * event. + */ + WRITE_ONCE(tmc->wakeup, ret); + + trace_tmigr_cpu_idle(tmc, nextexp); + raw_spin_unlock(&tmc->lock); + return ret; +} + +/** + * tmigr_quick_check() - Quick forecast of next tmigr event when CPU wants to + * go idle + * @nextevt: The next global timer expiry of the current CPU + * + * Return: + * * KTIME_MAX - when it is probable that nothing has to be done (not + * the only one in the level 0 group; and if it is the + * only one in level 0 group, but there are more than a + * single group active on the way to top level) + * * nextevt - when CPU is offline and has to handle timer on his own + * or when on the way to top in every group only a single + * child is active but @nextevt is before the lowest + * next_expiry encountered while walking up to top level. + * * next_expiry - value of lowest expiry encountered while walking groups + * if only a single child is active on each and @nextevt + * is after this lowest expiry. + */ +u64 tmigr_quick_check(u64 nextevt) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + struct tmigr_group *group = tmc->tmgroup; + + if (tmigr_is_not_available(tmc)) + return nextevt; + + if (WARN_ON_ONCE(tmc->idle)) + return nextevt; + + if (!tmigr_check_migrator_and_lonely(tmc->tmgroup, tmc->childmask)) + return KTIME_MAX; + + do { + if (!tmigr_check_lonely(group)) { + return KTIME_MAX; + } else { + /* + * Since current CPU is active, events may not be sorted + * from bottom to the top because the CPU's event is ignored + * up to the top and its sibling's events not propagated upwards. + * Thus keep track of the lowest observed expiry. + */ + nextevt = min_t(u64, nextevt, READ_ONCE(group->next_expiry)); + if (!group->parent) + return nextevt; + } + group = group->parent; + } while (group); + + return KTIME_MAX; +} + +static void tmigr_init_group(struct tmigr_group *group, unsigned int lvl, + int node) +{ + union tmigr_state s; + + raw_spin_lock_init(&group->lock); + + group->level = lvl; + group->numa_node = lvl < tmigr_crossnode_level ? node : NUMA_NO_NODE; + + group->num_children = 0; + + s.migrator = TMIGR_NONE; + s.active = 0; + s.seq = 0; + atomic_set(&group->migr_state, s.state); + + timerqueue_init_head(&group->events); + timerqueue_init(&group->groupevt.nextevt); + group->groupevt.nextevt.expires = KTIME_MAX; + WRITE_ONCE(group->next_expiry, KTIME_MAX); + group->groupevt.ignore = true; +} + +static struct tmigr_group *tmigr_get_group(unsigned int cpu, int node, + unsigned int lvl) +{ + struct tmigr_group *tmp, *group = NULL; + + lockdep_assert_held(&tmigr_mutex); + + /* Try to attach to an existing group first */ + list_for_each_entry(tmp, &tmigr_level_list[lvl], list) { + /* + * If @lvl is below the cross NUMA node level, check whether + * this group belongs to the same NUMA node. + */ + if (lvl < tmigr_crossnode_level && tmp->numa_node != node) + continue; + + /* Capacity left? */ + if (tmp->num_children >= TMIGR_CHILDREN_PER_GROUP) + continue; + + /* + * TODO: A possible further improvement: Make sure that all CPU + * siblings end up in the same group of the lowest level of the + * hierarchy. Rely on the topology sibling mask would be a + * reasonable solution. + */ + + group = tmp; + break; + } + + if (group) + return group; + + /* Allocate and set up a new group */ + group = kzalloc_node(sizeof(*group), GFP_KERNEL, node); + if (!group) + return ERR_PTR(-ENOMEM); + + tmigr_init_group(group, lvl, node); + + /* Setup successful. Add it to the hierarchy */ + list_add(&group->list, &tmigr_level_list[lvl]); + trace_tmigr_group_set(group); + return group; +} + +static void tmigr_connect_child_parent(struct tmigr_group *child, + struct tmigr_group *parent) +{ + union tmigr_state childstate; + + raw_spin_lock_irq(&child->lock); + raw_spin_lock_nested(&parent->lock, SINGLE_DEPTH_NESTING); + + child->parent = parent; + child->childmask = BIT(parent->num_children++); + + raw_spin_unlock(&parent->lock); + raw_spin_unlock_irq(&child->lock); + + trace_tmigr_connect_child_parent(child); + + /* + * To prevent inconsistent states, active children need to be active in + * the new parent as well. Inactive children are already marked inactive + * in the parent group: + * + * * When new groups were created by tmigr_setup_groups() starting from + * the lowest level (and not higher then one level below the current + * top level), then they are not active. They will be set active when + * the new online CPU comes active. + * + * * But if a new group above the current top level is required, it is + * mandatory to propagate the active state of the already existing + * child to the new parent. So tmigr_connect_child_parent() is + * executed with the formerly top level group (child) and the newly + * created group (parent). + */ + childstate.state = atomic_read(&child->migr_state); + if (childstate.migrator != TMIGR_NONE) { + struct tmigr_walk data; + + data.childmask = child->childmask; + + /* + * There is only one new level per time. When connecting the + * child and the parent and set the child active when the parent + * is inactive, the parent needs to be the uppermost + * level. Otherwise there went something wrong! + */ + WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent); + } +} + +static int tmigr_setup_groups(unsigned int cpu, unsigned int node) +{ + struct tmigr_group *group, *child, **stack; + int top = 0, err = 0, i = 0; + struct list_head *lvllist; + + stack = kcalloc(tmigr_hierarchy_levels, sizeof(*stack), GFP_KERNEL); + if (!stack) + return -ENOMEM; + + do { + group = tmigr_get_group(cpu, node, i); + if (IS_ERR(group)) { + err = PTR_ERR(group); + break; + } + + top = i; + stack[i++] = group; + + /* + * When booting only less CPUs of a system than CPUs are + * available, not all calculated hierarchy levels are required. + * + * The loop is aborted as soon as the highest level, which might + * be different from tmigr_hierarchy_levels, contains only a + * single group. + */ + if (group->parent || i == tmigr_hierarchy_levels || + (list_empty(&tmigr_level_list[i]) && + list_is_singular(&tmigr_level_list[i - 1]))) + break; + + } while (i < tmigr_hierarchy_levels); + + do { + group = stack[--i]; + + if (err < 0) { + list_del(&group->list); + kfree(group); + continue; + } + + WARN_ON_ONCE(i != group->level); + + /* + * Update tmc -> group / child -> group connection + */ + if (i == 0) { + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + raw_spin_lock_irq(&group->lock); + + tmc->tmgroup = group; + tmc->childmask = BIT(group->num_children++); + + raw_spin_unlock_irq(&group->lock); + + trace_tmigr_connect_cpu_parent(tmc); + + /* There are no children that need to be connected */ + continue; + } else { + child = stack[i - 1]; + tmigr_connect_child_parent(child, group); + } + + /* check if uppermost level was newly created */ + if (top != i) + continue; + + WARN_ON_ONCE(top == 0); + + lvllist = &tmigr_level_list[top]; + if (group->num_children == 1 && list_is_singular(lvllist)) { + lvllist = &tmigr_level_list[top - 1]; + list_for_each_entry(child, lvllist, list) { + if (child->parent) + continue; + + tmigr_connect_child_parent(child, group); + } + } + } while (i > 0); + + kfree(stack); + + return err; +} + +static int tmigr_add_cpu(unsigned int cpu) +{ + int node = cpu_to_node(cpu); + int ret; + + mutex_lock(&tmigr_mutex); + ret = tmigr_setup_groups(cpu, node); + mutex_unlock(&tmigr_mutex); + + return ret; +} + +static int tmigr_cpu_online(unsigned int cpu) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + int ret; + + /* First online attempt? Initialize CPU data */ + if (!tmc->tmgroup) { + raw_spin_lock_init(&tmc->lock); + + ret = tmigr_add_cpu(cpu); + if (ret < 0) + return ret; + + if (tmc->childmask == 0) + return -EINVAL; + + timerqueue_init(&tmc->cpuevt.nextevt); + tmc->cpuevt.nextevt.expires = KTIME_MAX; + tmc->cpuevt.ignore = true; + tmc->cpuevt.cpu = cpu; + + tmc->remote = false; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + } + raw_spin_lock_irq(&tmc->lock); + trace_tmigr_cpu_online(tmc); + tmc->idle = timer_base_is_idle(); + if (!tmc->idle) + __tmigr_cpu_activate(tmc); + tmc->online = true; + raw_spin_unlock_irq(&tmc->lock); + return 0; +} + +/* + * tmigr_trigger_active() - trigger a CPU to become active again + * + * This function is executed on a CPU which is part of cpu_online_mask, when the + * last active CPU in the hierarchy is offlining. With this, it is ensured that + * the other CPU is active and takes over the migrator duty. + */ +static long tmigr_trigger_active(void *unused) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + + WARN_ON_ONCE(!tmc->online || tmc->idle); + + return 0; +} + +static int tmigr_cpu_offline(unsigned int cpu) +{ + struct tmigr_cpu *tmc = this_cpu_ptr(&tmigr_cpu); + int migrator; + u64 firstexp; + + raw_spin_lock_irq(&tmc->lock); + tmc->online = false; + WRITE_ONCE(tmc->wakeup, KTIME_MAX); + + /* + * CPU has to handle the local events on his own, when on the way to + * offline; Therefore nextevt value is set to KTIME_MAX + */ + firstexp = __tmigr_cpu_deactivate(tmc, KTIME_MAX); + trace_tmigr_cpu_offline(tmc); + raw_spin_unlock_irq(&tmc->lock); + + if (firstexp != KTIME_MAX) { + migrator = cpumask_any_but(cpu_online_mask, cpu); + work_on_cpu(migrator, tmigr_trigger_active, NULL); + } + + return 0; +} + +static int __init tmigr_init(void) +{ + unsigned int cpulvl, nodelvl, cpus_per_node, i; + unsigned int nnodes = num_possible_nodes(); + unsigned int ncpus = num_possible_cpus(); + int ret = -ENOMEM; + + BUILD_BUG_ON_NOT_POWER_OF_2(TMIGR_CHILDREN_PER_GROUP); + + /* Nothing to do if running on UP */ + if (ncpus == 1) + return 0; + + /* + * Calculate the required hierarchy levels. Unfortunately there is no + * reliable information available, unless all possible CPUs have been + * brought up and all NUMA nodes are populated. + * + * Estimate the number of levels with the number of possible nodes and + * the number of possible CPUs. Assume CPUs are spread evenly across + * nodes. We cannot rely on cpumask_of_node() because it only works for + * online CPUs. + */ + cpus_per_node = DIV_ROUND_UP(ncpus, nnodes); + + /* Calc the hierarchy levels required to hold the CPUs of a node */ + cpulvl = DIV_ROUND_UP(order_base_2(cpus_per_node), + ilog2(TMIGR_CHILDREN_PER_GROUP)); + + /* Calculate the extra levels to connect all nodes */ + nodelvl = DIV_ROUND_UP(order_base_2(nnodes), + ilog2(TMIGR_CHILDREN_PER_GROUP)); + + tmigr_hierarchy_levels = cpulvl + nodelvl; + + /* + * If a NUMA node spawns more than one CPU level group then the next + * level(s) of the hierarchy contains groups which handle all CPU groups + * of the same NUMA node. The level above goes across NUMA nodes. Store + * this information for the setup code to decide in which level node + * matching is no longer required. + */ + tmigr_crossnode_level = cpulvl; + + tmigr_level_list = kcalloc(tmigr_hierarchy_levels, sizeof(struct list_head), GFP_KERNEL); + if (!tmigr_level_list) + goto err; + + for (i = 0; i < tmigr_hierarchy_levels; i++) + INIT_LIST_HEAD(&tmigr_level_list[i]); + + pr_info("Timer migration: %d hierarchy levels; %d children per group;" + " %d crossnode level\n", + tmigr_hierarchy_levels, TMIGR_CHILDREN_PER_GROUP, + tmigr_crossnode_level); + + ret = cpuhp_setup_state(CPUHP_AP_TMIGR_ONLINE, "tmigr:online", + tmigr_cpu_online, tmigr_cpu_offline); + if (ret) + goto err; + + return 0; + +err: + pr_err("Timer migration setup failed\n"); + return ret; +} +late_initcall(tmigr_init); diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h new file mode 100644 index 000000000000..6c37d94a37d9 --- /dev/null +++ b/kernel/time/timer_migration.h @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#ifndef _KERNEL_TIME_MIGRATION_H +#define _KERNEL_TIME_MIGRATION_H + +/* Per group capacity. Must be a power of 2! */ +#define TMIGR_CHILDREN_PER_GROUP 8 + +/** + * struct tmigr_event - a timer event associated to a CPU + * @nextevt: The node to enqueue an event in the parent group queue + * @cpu: The CPU to which this event belongs + * @ignore: Hint whether the event could be ignored; it is set when + * CPU or group is active; + */ +struct tmigr_event { + struct timerqueue_node nextevt; + unsigned int cpu; + bool ignore; +}; + +/** + * struct tmigr_group - timer migration hierarchy group + * @lock: Lock protecting the event information and group hierarchy + * information during setup + * @parent: Pointer to the parent group + * @groupevt: Next event of the group which is only used when the + * group is !active. The group event is then queued into + * the parent timer queue. + * Ignore bit of @groupevt is set when the group is active. + * @next_expiry: Base monotonic expiry time of the next event of the + * group; It is used for the racy lockless check whether a + * remote expiry is required; it is always reliable + * @events: Timer queue for child events queued in the group + * @migr_state: State of the group (see union tmigr_state) + * @level: Hierarchy level of the group; Required during setup + * @numa_node: Required for setup only to make sure CPU and low level + * group information is NUMA local. It is set to NUMA node + * as long as the group level is per NUMA node (level < + * tmigr_crossnode_level); otherwise it is set to + * NUMA_NO_NODE + * @num_children: Counter of group children to make sure the group is only + * filled with TMIGR_CHILDREN_PER_GROUP; Required for setup + * only + * @childmask: childmask of the group in the parent group; is set + * during setup and will never change; can be read + * lockless + * @list: List head that is added to the per level + * tmigr_level_list; is required during setup when a + * new group needs to be connected to the existing + * hierarchy groups + */ +struct tmigr_group { + raw_spinlock_t lock; + struct tmigr_group *parent; + struct tmigr_event groupevt; + u64 next_expiry; + struct timerqueue_head events; + atomic_t migr_state; + unsigned int level; + int numa_node; + unsigned int num_children; + u8 childmask; + struct list_head list; +}; + +/** + * struct tmigr_cpu - timer migration per CPU group + * @lock: Lock protecting the tmigr_cpu group information + * @online: Indicates whether the CPU is online; In deactivate path + * it is required to know whether the migrator in the top + * level group is to be set offline, while a timer is + * pending. Then another online CPU needs to be notified to + * take over the migrator role. Furthermore the information + * is required in CPU hotplug path as the CPU is able to go + * idle before the timer migration hierarchy hotplug AP is + * reached. During this phase, the CPU has to handle the + * global timers on its own and must not act as a migrator. + * @idle: Indicates whether the CPU is idle in the timer migration + * hierarchy + * @remote: Is set when timers of the CPU are expired remotely + * @tmgroup: Pointer to the parent group + * @childmask: childmask of tmigr_cpu in the parent group + * @wakeup: Stores the first timer when the timer migration + * hierarchy is completely idle and remote expiry was done; + * is returned to timer code in the idle path and is only + * used in idle path. + * @cpuevt: CPU event which could be enqueued into the parent group + */ +struct tmigr_cpu { + raw_spinlock_t lock; + bool online; + bool idle; + bool remote; + struct tmigr_group *tmgroup; + u8 childmask; + u64 wakeup; + struct tmigr_event cpuevt; +}; + +/** + * union tmigr_state - state of tmigr_group + * @state: Combined version of the state - only used for atomic + * read/cmpxchg function + * @struct: Split version of the state - only use the struct members to + * update information to stay independent of endianness + */ +union tmigr_state { + u32 state; + /** + * struct - split state of tmigr_group + * @active: Contains each childmask bit of the active children + * @migrator: Contains childmask of the child which is migrator + * @seq: Sequence counter needs to be increased when an update + * to the tmigr_state is done. It prevents a race when + * updates in the child groups are propagated in changed + * order. Detailed information about the scenario is + * given in the documentation at the begin of + * timer_migration.c. + */ + struct { + u8 active; + u8 migrator; + u16 seq; + } __packed; +}; + +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern void tmigr_handle_remote(void); +extern bool tmigr_requires_handle_remote(void); +extern void tmigr_cpu_activate(void); +extern u64 tmigr_cpu_deactivate(u64 nextevt); +extern u64 tmigr_cpu_new_timer(u64 nextevt); +extern u64 tmigr_quick_check(u64 nextevt); +#else +static inline void tmigr_handle_remote(void) { } +static inline bool tmigr_requires_handle_remote(void) { return false; } +static inline void tmigr_cpu_activate(void) { } +#endif + +#endif diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 7ac6c52b25eb..0a5c4efc73c3 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1412,14 +1412,14 @@ __bpf_kfunc int bpf_verify_pkcs7_signature(struct bpf_dynptr_kern *data_ptr, __bpf_kfunc_end_defs(); -BTF_SET8_START(key_sig_kfunc_set) +BTF_KFUNCS_START(key_sig_kfunc_set) BTF_ID_FLAGS(func, bpf_lookup_user_key, KF_ACQUIRE | KF_RET_NULL | KF_SLEEPABLE) BTF_ID_FLAGS(func, bpf_lookup_system_key, KF_ACQUIRE | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_key_put, KF_RELEASE) #ifdef CONFIG_SYSTEM_DATA_VERIFICATION BTF_ID_FLAGS(func, bpf_verify_pkcs7_signature, KF_SLEEPABLE) #endif -BTF_SET8_END(key_sig_kfunc_set) +BTF_KFUNCS_END(key_sig_kfunc_set) static const struct btf_kfunc_id_set bpf_key_sig_kfunc_set = { .owner = THIS_MODULE, @@ -1475,9 +1475,9 @@ __bpf_kfunc int bpf_get_file_xattr(struct file *file, const char *name__str, __bpf_kfunc_end_defs(); -BTF_SET8_START(fs_kfunc_set_ids) +BTF_KFUNCS_START(fs_kfunc_set_ids) BTF_ID_FLAGS(func, bpf_get_file_xattr, KF_SLEEPABLE | KF_TRUSTED_ARGS) -BTF_SET8_END(fs_kfunc_set_ids) +BTF_KFUNCS_END(fs_kfunc_set_ids) static int bpf_get_file_xattr_filter(const struct bpf_prog *prog, u32 kfunc_id) { @@ -1629,7 +1629,7 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_trace_vprintk: return bpf_get_trace_vprintk_proto(); default: - return bpf_base_func_proto(func_id); + return bpf_base_func_proto(func_id, prog); } } @@ -2679,6 +2679,7 @@ static void bpf_kprobe_multi_link_dealloc(struct bpf_link *link) static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, struct bpf_link_info *info) { + u64 __user *ucookies = u64_to_user_ptr(info->kprobe_multi.cookies); u64 __user *uaddrs = u64_to_user_ptr(info->kprobe_multi.addrs); struct bpf_kprobe_multi_link *kmulti_link; u32 ucount = info->kprobe_multi.count; @@ -2686,6 +2687,8 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, if (!uaddrs ^ !ucount) return -EINVAL; + if (ucookies && !ucount) + return -EINVAL; kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link); info->kprobe_multi.count = kmulti_link->cnt; @@ -2699,6 +2702,18 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link, else ucount = kmulti_link->cnt; + if (ucookies) { + if (kmulti_link->cookies) { + if (copy_to_user(ucookies, kmulti_link->cookies, ucount * sizeof(u64))) + return -EFAULT; + } else { + for (i = 0; i < ucount; i++) { + if (put_user(0, ucookies + i)) + return -EFAULT; + } + } + } + if (kallsyms_show_value(current_cred())) { if (copy_to_user(uaddrs, kmulti_link->addrs, ucount * sizeof(u64))) return -EFAULT; @@ -3241,7 +3256,7 @@ static int uprobe_prog_run(struct bpf_uprobe *uprobe, .uprobe = uprobe, }; struct bpf_prog *prog = link->link.prog; - bool sleepable = prog->aux->sleepable; + bool sleepable = prog->sleepable; struct bpf_run_ctx *old_run_ctx; int err = 0; diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index 6cd2a4e3afb8..9ff018245840 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -189,9 +189,6 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) { int size; - if (num <= 0) - return -EINVAL; - if (!fp->exit_handler) { fp->rethook = NULL; return 0; @@ -199,15 +196,16 @@ static int fprobe_init_rethook(struct fprobe *fp, int num) /* Initialize rethook if needed */ if (fp->nr_maxactive) - size = fp->nr_maxactive; + num = fp->nr_maxactive; else - size = num * num_possible_cpus() * 2; - if (size <= 0) + num *= num_possible_cpus() * 2; + if (num <= 0) return -EINVAL; + size = sizeof(struct fprobe_rethook_node) + fp->entry_data_size; + /* Initialize rethook */ - fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, - sizeof(struct fprobe_rethook_node), size); + fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler, size, num); if (IS_ERR(fp->rethook)) return PTR_ERR(fp->rethook); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index c060d5b47910..83ba342aef31 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -5331,7 +5331,7 @@ static int register_ftrace_function_nolock(struct ftrace_ops *ops); * not support ftrace_regs_caller but direct_call, use SAVE_ARGS so that it * jumps from ftrace_caller for multiple ftrace_ops. */ -#ifndef HAVE_DYNAMIC_FTRACE_WITH_REGS +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_REGS #define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_ARGS) #else #define MULTI_FLAGS (FTRACE_OPS_FL_DIRECT | FTRACE_OPS_FL_SAVE_REGS) diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index fd4bfe3ecf01..09df645ab9c7 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -384,7 +384,6 @@ struct rb_irq_work { struct irq_work work; wait_queue_head_t waiters; wait_queue_head_t full_waiters; - long wait_index; bool waiters_pending; bool full_waiters_pending; bool wakeup_full; @@ -756,8 +755,19 @@ static void rb_wake_up_waiters(struct irq_work *work) wake_up_all(&rbwork->waiters); if (rbwork->full_waiters_pending || rbwork->wakeup_full) { + /* Only cpu_buffer sets the above flags */ + struct ring_buffer_per_cpu *cpu_buffer = + container_of(rbwork, struct ring_buffer_per_cpu, irq_work); + + /* Called from interrupt context */ + raw_spin_lock(&cpu_buffer->reader_lock); rbwork->wakeup_full = false; rbwork->full_waiters_pending = false; + + /* Waking up all waiters, they will reset the shortest full */ + cpu_buffer->shortest_full = 0; + raw_spin_unlock(&cpu_buffer->reader_lock); + wake_up_all(&rbwork->full_waiters); } } @@ -798,122 +808,144 @@ void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu) rbwork = &cpu_buffer->irq_work; } - rbwork->wait_index++; - /* make sure the waiters see the new index */ - smp_wmb(); - /* This can be called in any context */ irq_work_queue(&rbwork->work); } +static bool rb_watermark_hit(struct trace_buffer *buffer, int cpu, int full) +{ + struct ring_buffer_per_cpu *cpu_buffer; + bool ret = false; + + /* Reads of all CPUs always waits for any data */ + if (cpu == RING_BUFFER_ALL_CPUS) + return !ring_buffer_empty(buffer); + + cpu_buffer = buffer->buffers[cpu]; + + if (!ring_buffer_empty_cpu(buffer, cpu)) { + unsigned long flags; + bool pagebusy; + + if (!full) + return true; + + raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); + pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; + ret = !pagebusy && full_hit(buffer, cpu, full); + + if (!ret && (!cpu_buffer->shortest_full || + cpu_buffer->shortest_full > full)) { + cpu_buffer->shortest_full = full; + } + raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); + } + return ret; +} + +static inline bool +rb_wait_cond(struct rb_irq_work *rbwork, struct trace_buffer *buffer, + int cpu, int full, ring_buffer_cond_fn cond, void *data) +{ + if (rb_watermark_hit(buffer, cpu, full)) + return true; + + if (cond(data)) + return true; + + /* + * The events can happen in critical sections where + * checking a work queue can cause deadlocks. + * After adding a task to the queue, this flag is set + * only to notify events to try to wake up the queue + * using irq_work. + * + * We don't clear it even if the buffer is no longer + * empty. The flag only causes the next event to run + * irq_work to do the work queue wake up. The worse + * that can happen if we race with !trace_empty() is that + * an event will cause an irq_work to try to wake up + * an empty queue. + * + * There's no reason to protect this flag either, as + * the work queue and irq_work logic will do the necessary + * synchronization for the wake ups. The only thing + * that is necessary is that the wake up happens after + * a task has been queued. It's OK for spurious wake ups. + */ + if (full) + rbwork->full_waiters_pending = true; + else + rbwork->waiters_pending = true; + + return false; +} + +/* + * The default wait condition for ring_buffer_wait() is to just to exit the + * wait loop the first time it is woken up. + */ +static bool rb_wait_once(void *data) +{ + long *once = data; + + /* wait_event() actually calls this twice before scheduling*/ + if (*once > 1) + return true; + + (*once)++; + return false; +} + /** * ring_buffer_wait - wait for input to the ring buffer * @buffer: buffer to wait on * @cpu: the cpu buffer to wait on * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS + * @cond: condition function to break out of wait (NULL to run once) + * @data: the data to pass to @cond. * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data) { struct ring_buffer_per_cpu *cpu_buffer; - DEFINE_WAIT(wait); - struct rb_irq_work *work; - long wait_index; + struct wait_queue_head *waitq; + struct rb_irq_work *rbwork; + long once = 0; int ret = 0; + if (!cond) { + cond = rb_wait_once; + data = &once; + } + /* * Depending on what the caller is waiting for, either any * data in any cpu buffer, or a specific buffer, put the * caller on the appropriate wait queue. */ if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; + rbwork = &buffer->irq_work; /* Full only makes sense on per cpu reads */ full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return -ENODEV; cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; - } - - wait_index = READ_ONCE(work->wait_index); - - while (true) { - if (full) - prepare_to_wait(&work->full_waiters, &wait, TASK_INTERRUPTIBLE); - else - prepare_to_wait(&work->waiters, &wait, TASK_INTERRUPTIBLE); - - /* - * The events can happen in critical sections where - * checking a work queue can cause deadlocks. - * After adding a task to the queue, this flag is set - * only to notify events to try to wake up the queue - * using irq_work. - * - * We don't clear it even if the buffer is no longer - * empty. The flag only causes the next event to run - * irq_work to do the work queue wake up. The worse - * that can happen if we race with !trace_empty() is that - * an event will cause an irq_work to try to wake up - * an empty queue. - * - * There's no reason to protect this flag either, as - * the work queue and irq_work logic will do the necessary - * synchronization for the wake ups. The only thing - * that is necessary is that the wake up happens after - * a task has been queued. It's OK for spurious wake ups. - */ - if (full) - work->full_waiters_pending = true; - else - work->waiters_pending = true; - - if (signal_pending(current)) { - ret = -EINTR; - break; - } - - if (cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) - break; - - if (cpu != RING_BUFFER_ALL_CPUS && - !ring_buffer_empty_cpu(buffer, cpu)) { - unsigned long flags; - bool pagebusy; - bool done; - - if (!full) - break; - - raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags); - pagebusy = cpu_buffer->reader_page == cpu_buffer->commit_page; - done = !pagebusy && full_hit(buffer, cpu, full); - - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; - raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags); - if (done) - break; - } - - schedule(); - - /* Make sure to see the new wait index */ - smp_rmb(); - if (wait_index != work->wait_index) - break; + rbwork = &cpu_buffer->irq_work; } if (full) - finish_wait(&work->full_waiters, &wait); + waitq = &rbwork->full_waiters; else - finish_wait(&work->waiters, &wait); + waitq = &rbwork->waiters; + + ret = wait_event_interruptible((*waitq), + rb_wait_cond(rbwork, buffer, cpu, full, cond, data)); return ret; } @@ -937,30 +969,44 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full) { struct ring_buffer_per_cpu *cpu_buffer; - struct rb_irq_work *work; + struct rb_irq_work *rbwork; if (cpu == RING_BUFFER_ALL_CPUS) { - work = &buffer->irq_work; + rbwork = &buffer->irq_work; full = 0; } else { if (!cpumask_test_cpu(cpu, buffer->cpumask)) return EPOLLERR; cpu_buffer = buffer->buffers[cpu]; - work = &cpu_buffer->irq_work; + rbwork = &cpu_buffer->irq_work; } if (full) { - poll_wait(filp, &work->full_waiters, poll_table); - work->full_waiters_pending = true; - if (!cpu_buffer->shortest_full || - cpu_buffer->shortest_full > full) - cpu_buffer->shortest_full = full; - } else { - poll_wait(filp, &work->waiters, poll_table); - work->waiters_pending = true; + poll_wait(filp, &rbwork->full_waiters, poll_table); + + if (rb_watermark_hit(buffer, cpu, full)) + return EPOLLIN | EPOLLRDNORM; + /* + * Only allow full_waiters_pending update to be seen after + * the shortest_full is set (in rb_watermark_hit). If the + * writer sees the full_waiters_pending flag set, it will + * compare the amount in the ring buffer to shortest_full. + * If the amount in the ring buffer is greater than the + * shortest_full percent, it will call the irq_work handler + * to wake up this list. The irq_handler will reset shortest_full + * back to zero. That's done under the reader_lock, but + * the below smp_mb() makes sure that the update to + * full_waiters_pending doesn't leak up into the above. + */ + smp_mb(); + rbwork->full_waiters_pending = true; + return 0; } + poll_wait(filp, &rbwork->waiters, poll_table); + rbwork->waiters_pending = true; + /* * There's a tight race between setting the waiters_pending and * checking if the ring buffer is empty. Once the waiters_pending bit @@ -976,9 +1022,6 @@ __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, */ smp_mb(); - if (full) - return full_hit(buffer, cpu, full) ? EPOLLIN | EPOLLRDNORM : 0; - if ((cpu == RING_BUFFER_ALL_CPUS && !ring_buffer_empty(buffer)) || (cpu != RING_BUFFER_ALL_CPUS && !ring_buffer_empty_cpu(buffer, cpu))) return EPOLLIN | EPOLLRDNORM; @@ -1009,7 +1052,7 @@ static inline u64 rb_time_stamp(struct trace_buffer *buffer) u64 ts; /* Skip retpolines :-( */ - if (IS_ENABLED(CONFIG_RETPOLINE) && likely(buffer->clock == trace_clock_local)) + if (IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) && likely(buffer->clock == trace_clock_local)) ts = trace_clock_local(); else ts = buffer->clock(); @@ -5877,6 +5920,10 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) if (psize <= BUF_PAGE_HDR_SIZE) return -EINVAL; + /* Size of a subbuf cannot be greater than the write counter */ + if (psize > RB_WRITE_MASK + 1) + return -EINVAL; + old_order = buffer->subbuf_order; old_size = buffer->subbuf_size; diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 9ff8a439d674..ab4c1a1fbda8 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -39,6 +39,7 @@ #include <linux/ctype.h> #include <linux/init.h> #include <linux/panic_notifier.h> +#include <linux/kmemleak.h> #include <linux/poll.h> #include <linux/nmi.h> #include <linux/fs.h> @@ -1532,7 +1533,7 @@ void disable_trace_on_warning(void) bool tracer_tracing_is_on(struct trace_array *tr) { if (tr->array_buffer.buffer) - return ring_buffer_record_is_on(tr->array_buffer.buffer); + return ring_buffer_record_is_set_on(tr->array_buffer.buffer); return !tr->buffer_disabled; } @@ -1954,15 +1955,36 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) #endif /* CONFIG_TRACER_MAX_TRACE */ +struct pipe_wait { + struct trace_iterator *iter; + int wait_index; +}; + +static bool wait_pipe_cond(void *data) +{ + struct pipe_wait *pwait = data; + struct trace_iterator *iter = pwait->iter; + + if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index) + return true; + + return iter->closed; +} + static int wait_on_pipe(struct trace_iterator *iter, int full) { + struct pipe_wait pwait; int ret; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + pwait.wait_index = atomic_read_acquire(&iter->wait_index); + pwait.iter = iter; + + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, + wait_pipe_cond, &pwait); #ifdef CONFIG_TRACER_MAX_TRACE /* @@ -2339,6 +2361,7 @@ static void free_saved_cmdlines_buffer(struct saved_cmdlines_buffer *s) int order = get_order(sizeof(*s) + s->cmdline_num * TASK_COMM_LEN); kfree(s->map_cmdline_to_pid); + kmemleak_free(s); free_pages((unsigned long)s, order); } @@ -2358,6 +2381,7 @@ static struct saved_cmdlines_buffer *allocate_cmdlines_buffer(unsigned int val) return NULL; s = page_address(page); + kmemleak_alloc(s, size, 1, GFP_KERNEL); memset(s, 0, sizeof(*s)); /* Round up to actual allocation */ @@ -5744,16 +5768,15 @@ static const char readme_msg[] = "\t args: <name>=fetcharg[:type]\n" "\t fetcharg: (%<register>|$<efield>), @<address>, @<symbol>[+|-<offset>],\n" #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API -#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n" +#ifdef CONFIG_PROBE_EVENTS_BTF_ARGS "\t <argname>[->field[->field|.field...]],\n" -#else - "\t $stack<index>, $stack, $retval, $comm, $arg<N>,\n" #endif #else "\t $stack<index>, $stack, $retval, $comm,\n" #endif "\t +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n" + "\t kernel return probes support: $retval, $arg<N>, $comm\n" "\t type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n" "\t b<bit-width>@<bit-offset>/<container-size>, ustring,\n" "\t symstr, <type>\\[<array-size>\\]\n" @@ -7290,6 +7313,8 @@ tracing_free_buffer_release(struct inode *inode, struct file *filp) return 0; } +#define TRACE_MARKER_MAX_SIZE 4096 + static ssize_t tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) @@ -7317,6 +7342,9 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if ((ssize_t)cnt < 0) return -EINVAL; + if (cnt > TRACE_MARKER_MAX_SIZE) + cnt = TRACE_MARKER_MAX_SIZE; + meta_size = sizeof(*entry) + 2; /* add '\0' and possible '\n' */ again: size = cnt + meta_size; @@ -7325,11 +7353,6 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, if (cnt < FAULTED_SIZE) size += FAULTED_SIZE - cnt; - if (size > TRACE_SEQ_BUFFER_SIZE) { - cnt -= size - TRACE_SEQ_BUFFER_SIZE; - goto again; - } - buffer = tr->array_buffer.buffer; event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size, tracing_gen_ctx()); @@ -8390,6 +8413,20 @@ tracing_buffers_read(struct file *filp, char __user *ubuf, return size; } +static int tracing_buffers_flush(struct file *file, fl_owner_t id) +{ + struct ftrace_buffer_info *info = file->private_data; + struct trace_iterator *iter = &info->iter; + + iter->closed = true; + /* Make sure the waiters see the new wait_index */ + (void)atomic_fetch_inc_release(&iter->wait_index); + + ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); + + return 0; +} + static int tracing_buffers_release(struct inode *inode, struct file *file) { struct ftrace_buffer_info *info = file->private_data; @@ -8401,12 +8438,6 @@ static int tracing_buffers_release(struct inode *inode, struct file *file) __trace_array_put(iter->tr); - iter->wait_index++; - /* Make sure the waiters see the new wait_index */ - smp_wmb(); - - ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); - if (info->spare) ring_buffer_free_read_page(iter->array_buffer->buffer, info->spare_cpu, info->spare); @@ -8489,6 +8520,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; + bool woken = false; int page_size; int entries, i; ssize_t ret = 0; @@ -8562,17 +8594,17 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { - long wait_index; if (ret) goto out; + if (woken) + goto out; + ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; - wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; @@ -8581,10 +8613,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, if (!tracer_tracing_is_on(iter->tr)) goto out; - /* Make sure we see the new wait_index */ - smp_rmb(); - if (wait_index != iter->wait_index) - goto out; + /* Iterate one more time to collect any new data then exit */ + woken = true; goto again; } @@ -8607,9 +8637,8 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned mutex_lock(&trace_types_lock); - iter->wait_index++; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); @@ -8622,6 +8651,7 @@ static const struct file_operations tracing_buffers_fops = { .read = tracing_buffers_read, .poll = tracing_buffers_poll, .release = tracing_buffers_release, + .flush = tracing_buffers_flush, .splice_read = tracing_buffers_splice_read, .unlocked_ioctl = tracing_buffers_ioctl, .llseek = no_llseek, diff --git a/kernel/trace/trace_btf.c b/kernel/trace/trace_btf.c index ca224d53bfdc..5bbdbcbbde3c 100644 --- a/kernel/trace/trace_btf.c +++ b/kernel/trace/trace_btf.c @@ -91,8 +91,8 @@ retry: for_each_member(i, type, member) { if (!member->name_off) { /* Anonymous union/struct: push it for later use */ - type = btf_type_skip_modifiers(btf, member->type, &tid); - if (type && top < BTF_ANON_STACK_MAX) { + if (btf_type_skip_modifiers(btf, member->type, &tid) && + top < BTF_ANON_STACK_MAX) { anon_stack[top].tid = tid; anon_stack[top++].offset = cur_offset + member->offset; diff --git a/kernel/trace/trace_eprobe.c b/kernel/trace/trace_eprobe.c index 03c851f57969..b0e0ec85912e 100644 --- a/kernel/trace/trace_eprobe.c +++ b/kernel/trace/trace_eprobe.c @@ -220,7 +220,7 @@ static struct trace_eprobe *alloc_event_probe(const char *group, if (!ep->event_system) goto error; - ret = trace_probe_init(&ep->tp, this_event, group, false); + ret = trace_probe_init(&ep->tp, this_event, group, false, nargs); if (ret < 0) goto error; @@ -390,8 +390,8 @@ static int get_eprobe_size(struct trace_probe *tp, void *rec) /* Note that we don't verify it, since the code does not come from user space */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, - void *base) +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) { unsigned long val; int ret; @@ -438,7 +438,7 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec) return; entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); - store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize); + store_trace_args(&entry[1], &edata->ep->tp, rec, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c index e7af286af4f1..c82b401a294d 100644 --- a/kernel/trace/trace_events_synth.c +++ b/kernel/trace/trace_events_synth.c @@ -441,8 +441,9 @@ static unsigned int trace_string(struct synth_trace_event *entry, if (is_dynamic) { union trace_synth_field *data = &entry->fields[*n_u64]; + len = fetch_store_strlen((unsigned long)str_val); data->as_dynamic.offset = struct_size(entry, fields, event->n_u64) + data_size; - data->as_dynamic.len = fetch_store_strlen((unsigned long)str_val); + data->as_dynamic.len = len; ret = fetch_store_string((unsigned long)str_val, &entry->fields[*n_u64], entry); diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c index 7d2ddbcfa377..4f4280815522 100644 --- a/kernel/trace/trace_fprobe.c +++ b/kernel/trace/trace_fprobe.c @@ -4,6 +4,7 @@ * Copyright (C) 2022 Google LLC. */ #define pr_fmt(fmt) "trace_fprobe: " fmt +#include <asm/ptrace.h> #include <linux/fprobe.h> #include <linux/module.h> @@ -129,8 +130,8 @@ static bool trace_fprobe_is_registered(struct trace_fprobe *tf) * from user space. */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, - void *base) +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) { struct pt_regs *regs = rec; unsigned long val; @@ -152,6 +153,9 @@ retry: case FETCH_OP_ARG: val = regs_get_kernel_argument(regs, code->param); break; + case FETCH_OP_EDATA: + val = *(unsigned long *)((unsigned long)edata + code->offset); + break; #endif case FETCH_NOP_SYMBOL: /* Ignore a place holder */ code++; @@ -184,7 +188,7 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs); + dsize = __get_data_size(&tf->tp, regs, NULL); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); @@ -194,7 +198,7 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, fbuffer.regs = regs; entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->ip = entry_ip; - store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } @@ -210,11 +214,24 @@ fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, } NOKPROBE_SYMBOL(fentry_trace_func); -/* Kretprobe handler */ +/* function exit handler */ +static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip, + unsigned long ret_ip, struct pt_regs *regs, + void *entry_data) +{ + struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); + + if (tf->tp.entry_arg) + store_trace_entry_data(entry_data, &tf->tp, regs); + + return 0; +} +NOKPROBE_SYMBOL(trace_fprobe_entry_handler) + static nokprobe_inline void __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, unsigned long ret_ip, struct pt_regs *regs, - struct trace_event_file *trace_file) + void *entry_data, struct trace_event_file *trace_file) { struct fexit_trace_entry_head *entry; struct trace_event_buffer fbuffer; @@ -227,7 +244,7 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tf->tp, regs); + dsize = __get_data_size(&tf->tp, regs, entry_data); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tf->tp.size + dsize); @@ -238,19 +255,19 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event); entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } static void fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs) + unsigned long ret_ip, struct pt_regs *regs, void *entry_data) { struct event_file_link *link; trace_probe_for_each_link_rcu(link, &tf->tp) - __fexit_trace_func(tf, entry_ip, ret_ip, regs, link->file); + __fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data, link->file); } NOKPROBE_SYMBOL(fexit_trace_func); @@ -269,7 +286,7 @@ static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, if (hlist_empty(head)) return 0; - dsize = __get_data_size(&tf->tp, regs); + dsize = __get_data_size(&tf->tp, regs, NULL); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); @@ -280,7 +297,7 @@ static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, entry->ip = entry_ip; memset(&entry[1], 0, dsize); - store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -289,7 +306,8 @@ NOKPROBE_SYMBOL(fentry_perf_func); static void fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, - unsigned long ret_ip, struct pt_regs *regs) + unsigned long ret_ip, struct pt_regs *regs, + void *entry_data) { struct trace_event_call *call = trace_probe_event_call(&tf->tp); struct fexit_trace_entry_head *entry; @@ -301,7 +319,7 @@ fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, if (hlist_empty(head)) return; - dsize = __get_data_size(&tf->tp, regs); + dsize = __get_data_size(&tf->tp, regs, entry_data); __size = sizeof(*entry) + tf->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); @@ -312,7 +330,7 @@ fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip, entry->func = entry_ip; entry->ret_ip = ret_ip; - store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } @@ -343,10 +361,10 @@ static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip, struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp); if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE)) - fexit_trace_func(tf, entry_ip, ret_ip, regs); + fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data); #ifdef CONFIG_PERF_EVENTS if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE)) - fexit_perf_func(tf, entry_ip, ret_ip, regs); + fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data); #endif } NOKPROBE_SYMBOL(fexit_dispatcher); @@ -389,7 +407,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group, tf->tpoint = tpoint; tf->fp.nr_maxactive = maxactive; - ret = trace_probe_init(&tf->tp, event, group, false); + ret = trace_probe_init(&tf->tp, event, group, false, nargs); if (ret < 0) goto error; @@ -1109,6 +1127,11 @@ static int __trace_fprobe_create(int argc, const char *argv[]) goto error; /* This can be -ENOMEM */ } + if (is_return && tf->tp.entry_arg) { + tf->fp.entry_handler = trace_fprobe_entry_handler; + tf->fp.entry_data_size = traceprobe_get_entry_data_size(&tf->tp); + } + ret = traceprobe_set_print_fmt(&tf->tp, is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL); if (ret < 0) diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c index c4c6e0e0068b..14099cc17fc9 100644 --- a/kernel/trace/trace_kprobe.c +++ b/kernel/trace/trace_kprobe.c @@ -290,7 +290,7 @@ static struct trace_kprobe *alloc_trace_kprobe(const char *group, INIT_HLIST_NODE(&tk->rp.kp.hlist); INIT_LIST_HEAD(&tk->rp.kp.list); - ret = trace_probe_init(&tk->tp, event, group, false); + ret = trace_probe_init(&tk->tp, event, group, false, nargs); if (ret < 0) goto error; @@ -740,6 +740,9 @@ static unsigned int number_of_same_symbols(char *func_name) return ctx.count; } +static int trace_kprobe_entry_handler(struct kretprobe_instance *ri, + struct pt_regs *regs); + static int __trace_kprobe_create(int argc, const char *argv[]) { /* @@ -948,6 +951,11 @@ static int __trace_kprobe_create(int argc, const char *argv[]) if (ret) goto error; /* This can be -ENOMEM */ } + /* entry handler for kretprobe */ + if (is_return && tk->tp.entry_arg) { + tk->rp.entry_handler = trace_kprobe_entry_handler; + tk->rp.data_size = traceprobe_get_entry_data_size(&tk->tp); + } ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL; ret = traceprobe_set_print_fmt(&tk->tp, ptype); @@ -1303,8 +1311,8 @@ static const struct file_operations kprobe_profile_ops = { /* Note that we don't verify it, since the code does not come from user space */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, - void *base) +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) { struct pt_regs *regs = rec; unsigned long val; @@ -1329,6 +1337,9 @@ retry: case FETCH_OP_ARG: val = regs_get_kernel_argument(regs, code->param); break; + case FETCH_OP_EDATA: + val = *(unsigned long *)((unsigned long)edata + code->offset); + break; #endif case FETCH_NOP_SYMBOL: /* Ignore a place holder */ code++; @@ -1359,7 +1370,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tk->tp, regs); + dsize = __get_data_size(&tk->tp, regs, NULL); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tk->tp.size + dsize); @@ -1368,7 +1379,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs, fbuffer.regs = regs; entry->ip = (unsigned long)tk->rp.kp.addr; - store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tk->tp, regs, NULL, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } @@ -1384,6 +1395,31 @@ kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs) NOKPROBE_SYMBOL(kprobe_trace_func); /* Kretprobe handler */ + +static int trace_kprobe_entry_handler(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + struct kretprobe *rp = get_kretprobe(ri); + struct trace_kprobe *tk; + + /* + * There is a small chance that get_kretprobe(ri) returns NULL when + * the kretprobe is unregister on another CPU between kretprobe's + * trampoline_handler and this function. + */ + if (unlikely(!rp)) + return -ENOENT; + + tk = container_of(rp, struct trace_kprobe, rp); + + /* store argument values into ri->data as entry data */ + if (tk->tp.entry_arg) + store_trace_entry_data(ri->data, &tk->tp, regs); + + return 0; +} + + static nokprobe_inline void __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, struct pt_regs *regs, @@ -1399,7 +1435,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, if (trace_trigger_soft_disabled(trace_file)) return; - dsize = __get_data_size(&tk->tp, regs); + dsize = __get_data_size(&tk->tp, regs, ri->data); entry = trace_event_buffer_reserve(&fbuffer, trace_file, sizeof(*entry) + tk->tp.size + dsize); @@ -1409,7 +1445,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, fbuffer.regs = regs; entry->func = (unsigned long)tk->rp.kp.addr; entry->ret_ip = get_kretprobe_retaddr(ri); - store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tk->tp, regs, ri->data, sizeof(*entry), dsize); trace_event_buffer_commit(&fbuffer); } @@ -1557,7 +1593,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) if (hlist_empty(head)) return 0; - dsize = __get_data_size(&tk->tp, regs); + dsize = __get_data_size(&tk->tp, regs, NULL); __size = sizeof(*entry) + tk->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); @@ -1568,7 +1604,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs) entry->ip = (unsigned long)tk->rp.kp.addr; memset(&entry[1], 0, dsize); - store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tk->tp, regs, NULL, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); return 0; @@ -1593,7 +1629,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, if (hlist_empty(head)) return; - dsize = __get_data_size(&tk->tp, regs); + dsize = __get_data_size(&tk->tp, regs, ri->data); __size = sizeof(*entry) + tk->tp.size + dsize; size = ALIGN(__size + sizeof(u32), sizeof(u64)); size -= sizeof(u32); @@ -1604,7 +1640,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri, entry->func = (unsigned long)tk->rp.kp.addr; entry->ret_ip = get_kretprobe_retaddr(ri); - store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize); + store_trace_args(&entry[1], &tk->tp, regs, ri->data, sizeof(*entry), dsize); perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs, head, NULL); } diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c index 3e7fa44dc2b2..d8b302d01083 100644 --- a/kernel/trace/trace_output.c +++ b/kernel/trace/trace_output.c @@ -1587,12 +1587,11 @@ static enum print_line_t trace_print_print(struct trace_iterator *iter, { struct print_entry *field; struct trace_seq *s = &iter->seq; - int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); seq_print_ip_sym(s, field->ip, flags); - trace_seq_printf(s, ": %.*s", max, field->buf); + trace_seq_printf(s, ": %s", field->buf); return trace_handle_return(s); } @@ -1601,11 +1600,10 @@ static enum print_line_t trace_print_raw(struct trace_iterator *iter, int flags, struct trace_event *event) { struct print_entry *field; - int max = iter->ent_size - offsetof(struct print_entry, buf); trace_assign_type(field, iter->ent); - trace_seq_printf(&iter->seq, "# %lx %.*s", field->ip, max, field->buf); + trace_seq_printf(&iter->seq, "# %lx %s", field->ip, field->buf); return trace_handle_return(&iter->seq); } diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 34289f9c6707..217169de0920 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -594,6 +594,8 @@ static int parse_btf_field(char *fieldname, const struct btf_type *type, return 0; } +static int __store_entry_arg(struct trace_probe *tp, int argnum); + static int parse_btf_arg(char *varname, struct fetch_insn **pcode, struct fetch_insn *end, struct traceprobe_parse_context *ctx) @@ -618,11 +620,7 @@ static int parse_btf_arg(char *varname, return -EOPNOTSUPP; } - if (ctx->flags & TPARG_FL_RETURN) { - if (strcmp(varname, "$retval") != 0) { - trace_probe_log_err(ctx->offset, NO_BTFARG); - return -ENOENT; - } + if (ctx->flags & TPARG_FL_RETURN && !strcmp(varname, "$retval")) { code->op = FETCH_OP_RETVAL; /* Check whether the function return type is not void */ if (query_btf_context(ctx) == 0) { @@ -654,11 +652,21 @@ static int parse_btf_arg(char *varname, const char *name = btf_name_by_offset(ctx->btf, params[i].name_off); if (name && !strcmp(name, varname)) { - code->op = FETCH_OP_ARG; - if (ctx->flags & TPARG_FL_TPOINT) - code->param = i + 1; - else - code->param = i; + if (tparg_is_function_entry(ctx->flags)) { + code->op = FETCH_OP_ARG; + if (ctx->flags & TPARG_FL_TPOINT) + code->param = i + 1; + else + code->param = i; + } else if (tparg_is_function_return(ctx->flags)) { + code->op = FETCH_OP_EDATA; + ret = __store_entry_arg(ctx->tp, i); + if (ret < 0) { + /* internal error */ + return ret; + } + code->offset = ret; + } tid = params[i].type; goto found; } @@ -755,6 +763,110 @@ static int check_prepare_btf_string_fetch(char *typename, #endif +#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API + +static int __store_entry_arg(struct trace_probe *tp, int argnum) +{ + struct probe_entry_arg *earg = tp->entry_arg; + bool match = false; + int i, offset; + + if (!earg) { + earg = kzalloc(sizeof(*tp->entry_arg), GFP_KERNEL); + if (!earg) + return -ENOMEM; + earg->size = 2 * tp->nr_args + 1; + earg->code = kcalloc(earg->size, sizeof(struct fetch_insn), + GFP_KERNEL); + if (!earg->code) { + kfree(earg); + return -ENOMEM; + } + /* Fill the code buffer with 'end' to simplify it */ + for (i = 0; i < earg->size; i++) + earg->code[i].op = FETCH_OP_END; + tp->entry_arg = earg; + } + + offset = 0; + for (i = 0; i < earg->size - 1; i++) { + switch (earg->code[i].op) { + case FETCH_OP_END: + earg->code[i].op = FETCH_OP_ARG; + earg->code[i].param = argnum; + earg->code[i + 1].op = FETCH_OP_ST_EDATA; + earg->code[i + 1].offset = offset; + return offset; + case FETCH_OP_ARG: + match = (earg->code[i].param == argnum); + break; + case FETCH_OP_ST_EDATA: + offset = earg->code[i].offset; + if (match) + return offset; + offset += sizeof(unsigned long); + break; + default: + break; + } + } + return -ENOSPC; +} + +int traceprobe_get_entry_data_size(struct trace_probe *tp) +{ + struct probe_entry_arg *earg = tp->entry_arg; + int i, size = 0; + + if (!earg) + return 0; + + for (i = 0; i < earg->size; i++) { + switch (earg->code[i].op) { + case FETCH_OP_END: + goto out; + case FETCH_OP_ST_EDATA: + size = earg->code[i].offset + sizeof(unsigned long); + break; + default: + break; + } + } +out: + return size; +} + +void store_trace_entry_data(void *edata, struct trace_probe *tp, struct pt_regs *regs) +{ + struct probe_entry_arg *earg = tp->entry_arg; + unsigned long val; + int i; + + if (!earg) + return; + + for (i = 0; i < earg->size; i++) { + struct fetch_insn *code = &earg->code[i]; + + switch (code->op) { + case FETCH_OP_ARG: + val = regs_get_kernel_argument(regs, code->param); + break; + case FETCH_OP_ST_EDATA: + *(unsigned long *)((unsigned long)edata + code->offset) = val; + break; + case FETCH_OP_END: + goto end; + default: + break; + } + } +end: + return; +} +NOKPROBE_SYMBOL(store_trace_entry_data) +#endif + #define PARAM_MAX_STACK (THREAD_SIZE / sizeof(unsigned long)) /* Parse $vars. @orig_arg points '$', which syncs to @ctx->offset */ @@ -830,7 +942,7 @@ static int parse_probe_vars(char *orig_arg, const struct fetch_type *t, #ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API len = str_has_prefix(arg, "arg"); - if (len && tparg_is_function_entry(ctx->flags)) { + if (len) { ret = kstrtoul(arg + len, 10, ¶m); if (ret) goto inval; @@ -839,15 +951,29 @@ static int parse_probe_vars(char *orig_arg, const struct fetch_type *t, err = TP_ERR_BAD_ARG_NUM; goto inval; } + param--; /* argN starts from 1, but internal arg[N] starts from 0 */ - code->op = FETCH_OP_ARG; - code->param = (unsigned int)param - 1; - /* - * The tracepoint probe will probe a stub function, and the - * first parameter of the stub is a dummy and should be ignored. - */ - if (ctx->flags & TPARG_FL_TPOINT) - code->param++; + if (tparg_is_function_entry(ctx->flags)) { + code->op = FETCH_OP_ARG; + code->param = (unsigned int)param; + /* + * The tracepoint probe will probe a stub function, and the + * first parameter of the stub is a dummy and should be ignored. + */ + if (ctx->flags & TPARG_FL_TPOINT) + code->param++; + } else if (tparg_is_function_return(ctx->flags)) { + /* function entry argument access from return probe */ + ret = __store_entry_arg(ctx->tp, param); + if (ret < 0) /* This error should be an internal error */ + return ret; + + code->op = FETCH_OP_EDATA; + code->offset = ret; + } else { + err = TP_ERR_NOFENTRY_ARGS; + goto inval; + } return 0; } #endif @@ -1037,7 +1163,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type, break; default: if (isalpha(arg[0]) || arg[0] == '_') { /* BTF variable */ - if (!tparg_is_function_entry(ctx->flags)) { + if (!tparg_is_function_entry(ctx->flags) && + !tparg_is_function_return(ctx->flags)) { trace_probe_log_err(ctx->offset, NOSUP_BTFARG); return -EINVAL; } @@ -1090,67 +1217,45 @@ static int __parse_bitfield_probe_arg(const char *bf, return (BYTES_TO_BITS(t->size) < (bw + bo)) ? -EINVAL : 0; } -/* String length checking wrapper */ -static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, - struct probe_arg *parg, - struct traceprobe_parse_context *ctx) +/* Split type part from @arg and return it. */ +static char *parse_probe_arg_type(char *arg, struct probe_arg *parg, + struct traceprobe_parse_context *ctx) { - struct fetch_insn *code, *scode, *tmp = NULL; - char *t, *t2, *t3; - int ret, len; - char *arg; - - arg = kstrdup(argv, GFP_KERNEL); - if (!arg) - return -ENOMEM; - - ret = -EINVAL; - len = strlen(arg); - if (len > MAX_ARGSTR_LEN) { - trace_probe_log_err(ctx->offset, ARG_TOO_LONG); - goto out; - } else if (len == 0) { - trace_probe_log_err(ctx->offset, NO_ARG_BODY); - goto out; - } - - ret = -ENOMEM; - parg->comm = kstrdup(arg, GFP_KERNEL); - if (!parg->comm) - goto out; + char *t = NULL, *t2, *t3; + int offs; - ret = -EINVAL; t = strchr(arg, ':'); if (t) { - *t = '\0'; - t2 = strchr(++t, '['); + *t++ = '\0'; + t2 = strchr(t, '['); if (t2) { *t2++ = '\0'; t3 = strchr(t2, ']'); if (!t3) { - int offs = t2 + strlen(t2) - arg; + offs = t2 + strlen(t2) - arg; trace_probe_log_err(ctx->offset + offs, ARRAY_NO_CLOSE); - goto out; + return ERR_PTR(-EINVAL); } else if (t3[1] != '\0') { trace_probe_log_err(ctx->offset + t3 + 1 - arg, BAD_ARRAY_SUFFIX); - goto out; + return ERR_PTR(-EINVAL); } *t3 = '\0'; if (kstrtouint(t2, 0, &parg->count) || !parg->count) { trace_probe_log_err(ctx->offset + t2 - arg, BAD_ARRAY_NUM); - goto out; + return ERR_PTR(-EINVAL); } if (parg->count > MAX_ARRAY_LEN) { trace_probe_log_err(ctx->offset + t2 - arg, ARRAY_TOO_BIG); - goto out; + return ERR_PTR(-EINVAL); } } } + offs = t ? t - arg : 0; /* * Since $comm and immediate string can not be dereferenced, @@ -1161,74 +1266,52 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, strncmp(arg, "\\\"", 2) == 0)) { /* The type of $comm must be "string", and not an array type. */ if (parg->count || (t && strcmp(t, "string"))) { - trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), - NEED_STRING_TYPE); - goto out; + trace_probe_log_err(ctx->offset + offs, NEED_STRING_TYPE); + return ERR_PTR(-EINVAL); } parg->type = find_fetch_type("string", ctx->flags); } else parg->type = find_fetch_type(t, ctx->flags); + if (!parg->type) { - trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), BAD_TYPE); - goto out; + trace_probe_log_err(ctx->offset + offs, BAD_TYPE); + return ERR_PTR(-EINVAL); } - code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL); - if (!code) - goto out; - code[FETCH_INSN_MAX - 1].op = FETCH_OP_END; - - ctx->last_type = NULL; - ret = parse_probe_arg(arg, parg->type, &code, &code[FETCH_INSN_MAX - 1], - ctx); - if (ret) - goto fail; - - /* Update storing type if BTF is available */ - if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) && - ctx->last_type) { - if (!t) { - parg->type = find_fetch_type_from_btf_type(ctx); - } else if (strstr(t, "string")) { - ret = check_prepare_btf_string_fetch(t, &code, ctx); - if (ret) - goto fail; - } - } - parg->offset = *size; - *size += parg->type->size * (parg->count ?: 1); + return t; +} - if (parg->count) { - len = strlen(parg->type->fmttype) + 6; - parg->fmt = kmalloc(len, GFP_KERNEL); - if (!parg->fmt) { - ret = -ENOMEM; - goto out; - } - snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype, - parg->count); - } +/* After parsing, adjust the fetch_insn according to the probe_arg */ +static int finalize_fetch_insn(struct fetch_insn *code, + struct probe_arg *parg, + char *type, + int type_offset, + struct traceprobe_parse_context *ctx) +{ + struct fetch_insn *scode; + int ret; - ret = -EINVAL; /* Store operation */ if (parg->type->is_string) { + /* Check bad combination of the type and the last fetch_insn. */ if (!strcmp(parg->type->name, "symstr")) { if (code->op != FETCH_OP_REG && code->op != FETCH_OP_STACK && code->op != FETCH_OP_RETVAL && code->op != FETCH_OP_ARG && code->op != FETCH_OP_DEREF && code->op != FETCH_OP_TP_ARG) { - trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), + trace_probe_log_err(ctx->offset + type_offset, BAD_SYMSTRING); - goto fail; + return -EINVAL; } } else { if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF && code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM && code->op != FETCH_OP_DATA && code->op != FETCH_OP_TP_ARG) { - trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), + trace_probe_log_err(ctx->offset + type_offset, BAD_STRING); - goto fail; + return -EINVAL; } } + if (!strcmp(parg->type->name, "symstr") || (code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM || code->op == FETCH_OP_DATA) || code->op == FETCH_OP_TP_ARG || @@ -1244,9 +1327,10 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, code++; if (code->op != FETCH_OP_NOP) { trace_probe_log_err(ctx->offset, TOO_MANY_OPS); - goto fail; + return -EINVAL; } } + /* If op == DEREF, replace it with STRING */ if (!strcmp(parg->type->name, "ustring") || code->op == FETCH_OP_UDEREF) @@ -1267,47 +1351,134 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, code++; if (code->op != FETCH_OP_NOP) { trace_probe_log_err(ctx->offset, TOO_MANY_OPS); - goto fail; + return -E2BIG; } code->op = FETCH_OP_ST_RAW; code->size = parg->type->size; } + + /* Save storing fetch_insn. */ scode = code; + /* Modify operation */ - if (t != NULL) { - ret = __parse_bitfield_probe_arg(t, parg->type, &code); + if (type != NULL) { + /* Bitfield needs a special fetch_insn. */ + ret = __parse_bitfield_probe_arg(type, parg->type, &code); if (ret) { - trace_probe_log_err(ctx->offset + t - arg, BAD_BITFIELD); - goto fail; + trace_probe_log_err(ctx->offset + type_offset, BAD_BITFIELD); + return ret; } } else if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) && ctx->last_type) { + /* If user not specified the type, try parsing BTF bitfield. */ ret = parse_btf_bitfield(&code, ctx); if (ret) - goto fail; + return ret; } - ret = -EINVAL; + /* Loop(Array) operation */ if (parg->count) { if (scode->op != FETCH_OP_ST_MEM && scode->op != FETCH_OP_ST_STRING && scode->op != FETCH_OP_ST_USTRING) { - trace_probe_log_err(ctx->offset + (t ? (t - arg) : 0), - BAD_STRING); - goto fail; + trace_probe_log_err(ctx->offset + type_offset, BAD_STRING); + return -EINVAL; } code++; if (code->op != FETCH_OP_NOP) { trace_probe_log_err(ctx->offset, TOO_MANY_OPS); - goto fail; + return -E2BIG; } code->op = FETCH_OP_LP_ARRAY; code->param = parg->count; } + + /* Finalize the fetch_insn array. */ code++; code->op = FETCH_OP_END; - ret = 0; + return 0; +} + +/* String length checking wrapper */ +static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, + struct probe_arg *parg, + struct traceprobe_parse_context *ctx) +{ + struct fetch_insn *code, *tmp = NULL; + char *type, *arg; + int ret, len; + + len = strlen(argv); + if (len > MAX_ARGSTR_LEN) { + trace_probe_log_err(ctx->offset, ARG_TOO_LONG); + return -E2BIG; + } else if (len == 0) { + trace_probe_log_err(ctx->offset, NO_ARG_BODY); + return -EINVAL; + } + + arg = kstrdup(argv, GFP_KERNEL); + if (!arg) + return -ENOMEM; + + parg->comm = kstrdup(arg, GFP_KERNEL); + if (!parg->comm) { + ret = -ENOMEM; + goto out; + } + + type = parse_probe_arg_type(arg, parg, ctx); + if (IS_ERR(type)) { + ret = PTR_ERR(type); + goto out; + } + + code = tmp = kcalloc(FETCH_INSN_MAX, sizeof(*code), GFP_KERNEL); + if (!code) { + ret = -ENOMEM; + goto out; + } + code[FETCH_INSN_MAX - 1].op = FETCH_OP_END; + + ctx->last_type = NULL; + ret = parse_probe_arg(arg, parg->type, &code, &code[FETCH_INSN_MAX - 1], + ctx); + if (ret < 0) + goto fail; + + /* Update storing type if BTF is available */ + if (IS_ENABLED(CONFIG_PROBE_EVENTS_BTF_ARGS) && + ctx->last_type) { + if (!type) { + parg->type = find_fetch_type_from_btf_type(ctx); + } else if (strstr(type, "string")) { + ret = check_prepare_btf_string_fetch(type, &code, ctx); + if (ret) + goto fail; + } + } + parg->offset = *size; + *size += parg->type->size * (parg->count ?: 1); + + if (parg->count) { + len = strlen(parg->type->fmttype) + 6; + parg->fmt = kmalloc(len, GFP_KERNEL); + if (!parg->fmt) { + ret = -ENOMEM; + goto out; + } + snprintf(parg->fmt, len, "%s[%d]", parg->type->fmttype, + parg->count); + } + + ret = finalize_fetch_insn(code, parg, type, type ? type - arg : 0, ctx); + if (ret < 0) + goto fail; + + for (; code < tmp + FETCH_INSN_MAX; code++) + if (code->op == FETCH_OP_END) + break; /* Shrink down the code buffer */ parg->code = kcalloc(code - tmp + 1, sizeof(*code), GFP_KERNEL); if (!parg->code) @@ -1316,7 +1487,7 @@ static int traceprobe_parse_probe_arg_body(const char *argv, ssize_t *size, memcpy(parg->code, tmp, sizeof(*code) * (code - tmp + 1)); fail: - if (ret) { + if (ret < 0) { for (code = tmp; code < tmp + FETCH_INSN_MAX; code++) if (code->op == FETCH_NOP_SYMBOL || code->op == FETCH_OP_DATA) @@ -1379,9 +1550,7 @@ int traceprobe_parse_probe_arg(struct trace_probe *tp, int i, const char *arg, struct probe_arg *parg = &tp->args[i]; const char *body; - /* Increment count for freeing args in error case */ - tp->nr_args++; - + ctx->tp = tp; body = strchr(arg, '='); if (body) { if (body - arg > MAX_ARG_NAME_LEN) { @@ -1438,7 +1607,8 @@ static int argv_has_var_arg(int argc, const char *argv[], int *args_idx, if (str_has_prefix(argv[i], "$arg")) { trace_probe_log_set_index(i + 2); - if (!tparg_is_function_entry(ctx->flags)) { + if (!tparg_is_function_entry(ctx->flags) && + !tparg_is_function_return(ctx->flags)) { trace_probe_log_err(0, NOFENTRY_ARGS); return -EINVAL; } @@ -1761,12 +1931,18 @@ void trace_probe_cleanup(struct trace_probe *tp) for (i = 0; i < tp->nr_args; i++) traceprobe_free_probe_arg(&tp->args[i]); + if (tp->entry_arg) { + kfree(tp->entry_arg->code); + kfree(tp->entry_arg); + tp->entry_arg = NULL; + } + if (tp->event) trace_probe_unlink(tp); } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group, bool alloc_filter) + const char *group, bool alloc_filter, int nargs) { struct trace_event_call *call; size_t size = sizeof(struct trace_probe_event); @@ -1802,6 +1978,11 @@ int trace_probe_init(struct trace_probe *tp, const char *event, goto error; } + tp->nr_args = nargs; + /* Make sure pointers in args[] are NULL */ + if (nargs) + memset(tp->args, 0, sizeof(tp->args[0]) * nargs); + return 0; error: diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h index c1877d018269..cef3a50628a3 100644 --- a/kernel/trace/trace_probe.h +++ b/kernel/trace/trace_probe.h @@ -92,6 +92,7 @@ enum fetch_op { FETCH_OP_ARG, /* Function argument : .param */ FETCH_OP_FOFFS, /* File offset: .immediate */ FETCH_OP_DATA, /* Allocated data: .data */ + FETCH_OP_EDATA, /* Entry data: .offset */ // Stage 2 (dereference) op FETCH_OP_DEREF, /* Dereference: .offset */ FETCH_OP_UDEREF, /* User-space Dereference: .offset */ @@ -102,6 +103,7 @@ enum fetch_op { FETCH_OP_ST_STRING, /* String: .offset, .size */ FETCH_OP_ST_USTRING, /* User String: .offset, .size */ FETCH_OP_ST_SYMSTR, /* Kernel Symbol String: .offset, .size */ + FETCH_OP_ST_EDATA, /* Store Entry Data: .offset */ // Stage 4 (modify) op FETCH_OP_MOD_BF, /* Bitfield: .basesize, .lshift, .rshift */ // Stage 5 (loop) op @@ -232,6 +234,11 @@ struct probe_arg { const struct fetch_type *type; /* Type of this argument */ }; +struct probe_entry_arg { + struct fetch_insn *code; + unsigned int size; /* The entry data size */ +}; + struct trace_uprobe_filter { rwlock_t rwlock; int nr_systemwide; @@ -253,6 +260,7 @@ struct trace_probe { struct trace_probe_event *event; ssize_t size; /* trace entry size */ unsigned int nr_args; + struct probe_entry_arg *entry_arg; /* This is only for return probe */ struct probe_arg args[]; }; @@ -338,7 +346,7 @@ static inline bool trace_probe_has_single_file(struct trace_probe *tp) } int trace_probe_init(struct trace_probe *tp, const char *event, - const char *group, bool alloc_filter); + const char *group, bool alloc_filter, int nargs); void trace_probe_cleanup(struct trace_probe *tp); int trace_probe_append(struct trace_probe *tp, struct trace_probe *to); void trace_probe_unlink(struct trace_probe *tp); @@ -355,6 +363,18 @@ int trace_probe_create(const char *raw_command, int (*createfn)(int, const char int trace_probe_print_args(struct trace_seq *s, struct probe_arg *args, int nr_args, u8 *data, void *field); +#ifdef CONFIG_HAVE_FUNCTION_ARG_ACCESS_API +int traceprobe_get_entry_data_size(struct trace_probe *tp); +/* This is a runtime function to store entry data */ +void store_trace_entry_data(void *edata, struct trace_probe *tp, struct pt_regs *regs); +#else /* !CONFIG_HAVE_FUNCTION_ARG_ACCESS_API */ +static inline int traceprobe_get_entry_data_size(struct trace_probe *tp) +{ + return 0; +} +#define store_trace_entry_data(edata, tp, regs) do { } while (0) +#endif + #define trace_probe_for_each_link(pos, tp) \ list_for_each_entry(pos, &(tp)->event->files, list) #define trace_probe_for_each_link_rcu(pos, tp) \ @@ -381,6 +401,11 @@ static inline bool tparg_is_function_entry(unsigned int flags) return (flags & TPARG_FL_LOC_MASK) == (TPARG_FL_KERNEL | TPARG_FL_FENTRY); } +static inline bool tparg_is_function_return(unsigned int flags) +{ + return (flags & TPARG_FL_LOC_MASK) == (TPARG_FL_KERNEL | TPARG_FL_RETURN); +} + struct traceprobe_parse_context { struct trace_event_call *event; /* BTF related parameters */ @@ -392,6 +417,7 @@ struct traceprobe_parse_context { const struct btf_type *last_type; /* Saved type */ u32 last_bitoffs; /* Saved bitoffs */ u32 last_bitsize; /* Saved bitsize */ + struct trace_probe *tp; unsigned int flags; int offset; }; @@ -506,7 +532,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call, C(NO_BTFARG, "This variable is not found at this probe point"),\ C(NO_BTF_ENTRY, "No BTF entry for this probe point"), \ C(BAD_VAR_ARGS, "$arg* must be an independent parameter without name etc."),\ - C(NOFENTRY_ARGS, "$arg* can be used only on function entry"), \ + C(NOFENTRY_ARGS, "$arg* can be used only on function entry or exit"), \ C(DOUBLE_ARGS, "$arg* can be used only once in the parameters"), \ C(ARGS_2LONG, "$arg* failed because the argument list is too long"), \ C(ARGIDX_2BIG, "$argN index is too big"), \ diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 3935b347f874..2caf0d2afb32 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -54,7 +54,7 @@ fetch_apply_bitfield(struct fetch_insn *code, void *buf) * If dest is NULL, don't store result and return required dynamic data size. */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, void *dest, void *base); static nokprobe_inline int fetch_store_strlen(unsigned long addr); static nokprobe_inline int @@ -232,7 +232,7 @@ array: /* Sum up total data length for dynamic arrays (strings) */ static nokprobe_inline int -__get_data_size(struct trace_probe *tp, struct pt_regs *regs) +__get_data_size(struct trace_probe *tp, struct pt_regs *regs, void *edata) { struct probe_arg *arg; int i, len, ret = 0; @@ -240,7 +240,7 @@ __get_data_size(struct trace_probe *tp, struct pt_regs *regs) for (i = 0; i < tp->nr_args; i++) { arg = tp->args + i; if (unlikely(arg->dynamic)) { - len = process_fetch_insn(arg->code, regs, NULL, NULL); + len = process_fetch_insn(arg->code, regs, edata, NULL, NULL); if (len > 0) ret += len; } @@ -251,7 +251,7 @@ __get_data_size(struct trace_probe *tp, struct pt_regs *regs) /* Store the value of each argument */ static nokprobe_inline void -store_trace_args(void *data, struct trace_probe *tp, void *rec, +store_trace_args(void *data, struct trace_probe *tp, void *rec, void *edata, int header_size, int maxlen) { struct probe_arg *arg; @@ -266,7 +266,7 @@ store_trace_args(void *data, struct trace_probe *tp, void *rec, /* Point the dynamic data area if needed */ if (unlikely(arg->dynamic)) *dl = make_data_loc(maxlen, dyndata - base); - ret = process_fetch_insn(arg->code, rec, dl, base); + ret = process_fetch_insn(arg->code, rec, edata, dl, base); if (arg->dynamic && likely(ret > 0)) { dyndata += ret; maxlen -= ret; diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index a84b85d8aac1..9e461362450a 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -211,8 +211,8 @@ static unsigned long translate_user_vaddr(unsigned long file_offset) /* Note that we don't verify it, since the code does not come from user space */ static int -process_fetch_insn(struct fetch_insn *code, void *rec, void *dest, - void *base) +process_fetch_insn(struct fetch_insn *code, void *rec, void *edata, + void *dest, void *base) { struct pt_regs *regs = rec; unsigned long val; @@ -337,7 +337,7 @@ alloc_trace_uprobe(const char *group, const char *event, int nargs, bool is_ret) if (!tu) return ERR_PTR(-ENOMEM); - ret = trace_probe_init(&tu->tp, event, group, true); + ret = trace_probe_init(&tu->tp, event, group, true, nargs); if (ret < 0) goto error; @@ -1490,11 +1490,11 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs) if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; - dsize = __get_data_size(&tu->tp, regs); + dsize = __get_data_size(&tu->tp, regs, NULL); esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); ucb = uprobe_buffer_get(); - store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); + store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) ret |= uprobe_trace_func(tu, regs, ucb, dsize); @@ -1525,11 +1525,11 @@ static int uretprobe_dispatcher(struct uprobe_consumer *con, if (WARN_ON_ONCE(!uprobe_cpu_buffer)) return 0; - dsize = __get_data_size(&tu->tp, regs); + dsize = __get_data_size(&tu->tp, regs, NULL); esize = SIZEOF_TRACE_ENTRY(is_ret_probe(tu)); ucb = uprobe_buffer_get(); - store_trace_args(ucb->buf, &tu->tp, regs, esize, dsize); + store_trace_args(ucb->buf, &tu->tp, regs, NULL, esize, dsize); if (trace_probe_test_flag(&tu->tp, TP_FLAG_TRACE)) uretprobe_trace_func(tu, func, regs, ucb, dsize); diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index ce4d99df5f0e..0b0b95418b16 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -931,7 +931,7 @@ static ssize_t map_write(struct file *file, const char __user *buf, struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; - char *kbuf = NULL, *pos, *next_line; + char *kbuf, *pos, *next_line; ssize_t ret; /* Only allow < page size writes at the beginning of the file */ diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c new file mode 100644 index 000000000000..f95516cd45bb --- /dev/null +++ b/kernel/vmcore_info.c @@ -0,0 +1,233 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * crash.c - kernel crash support code. + * Copyright (C) 2002-2004 Eric Biederman <ebiederm@xmission.com> + */ + +#include <linux/buildid.h> +#include <linux/init.h> +#include <linux/utsname.h> +#include <linux/vmalloc.h> +#include <linux/sizes.h> +#include <linux/kexec.h> +#include <linux/memory.h> +#include <linux/cpuhotplug.h> +#include <linux/memblock.h> +#include <linux/kmemleak.h> + +#include <asm/page.h> +#include <asm/sections.h> + +#include <crypto/sha1.h> + +#include "kallsyms_internal.h" +#include "kexec_internal.h" + +/* vmcoreinfo stuff */ +unsigned char *vmcoreinfo_data; +size_t vmcoreinfo_size; +u32 *vmcoreinfo_note; + +/* trusted vmcoreinfo, e.g. we can make a copy in the crash memory */ +static unsigned char *vmcoreinfo_data_safecopy; + +Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type, + void *data, size_t data_len) +{ + struct elf_note *note = (struct elf_note *)buf; + + note->n_namesz = strlen(name) + 1; + note->n_descsz = data_len; + note->n_type = type; + buf += DIV_ROUND_UP(sizeof(*note), sizeof(Elf_Word)); + memcpy(buf, name, note->n_namesz); + buf += DIV_ROUND_UP(note->n_namesz, sizeof(Elf_Word)); + memcpy(buf, data, data_len); + buf += DIV_ROUND_UP(data_len, sizeof(Elf_Word)); + + return buf; +} + +void final_note(Elf_Word *buf) +{ + memset(buf, 0, sizeof(struct elf_note)); +} + +static void update_vmcoreinfo_note(void) +{ + u32 *buf = vmcoreinfo_note; + + if (!vmcoreinfo_size) + return; + buf = append_elf_note(buf, VMCOREINFO_NOTE_NAME, 0, vmcoreinfo_data, + vmcoreinfo_size); + final_note(buf); +} + +void crash_update_vmcoreinfo_safecopy(void *ptr) +{ + if (ptr) + memcpy(ptr, vmcoreinfo_data, vmcoreinfo_size); + + vmcoreinfo_data_safecopy = ptr; +} + +void crash_save_vmcoreinfo(void) +{ + if (!vmcoreinfo_note) + return; + + /* Use the safe copy to generate vmcoreinfo note if have */ + if (vmcoreinfo_data_safecopy) + vmcoreinfo_data = vmcoreinfo_data_safecopy; + + vmcoreinfo_append_str("CRASHTIME=%lld\n", ktime_get_real_seconds()); + update_vmcoreinfo_note(); +} + +void vmcoreinfo_append_str(const char *fmt, ...) +{ + va_list args; + char buf[0x50]; + size_t r; + + va_start(args, fmt); + r = vscnprintf(buf, sizeof(buf), fmt, args); + va_end(args); + + r = min(r, (size_t)VMCOREINFO_BYTES - vmcoreinfo_size); + + memcpy(&vmcoreinfo_data[vmcoreinfo_size], buf, r); + + vmcoreinfo_size += r; + + WARN_ONCE(vmcoreinfo_size == VMCOREINFO_BYTES, + "vmcoreinfo data exceeds allocated size, truncating"); +} + +/* + * provide an empty default implementation here -- architecture + * code may override this + */ +void __weak arch_crash_save_vmcoreinfo(void) +{} + +phys_addr_t __weak paddr_vmcoreinfo_note(void) +{ + return __pa(vmcoreinfo_note); +} +EXPORT_SYMBOL(paddr_vmcoreinfo_note); + +static int __init crash_save_vmcoreinfo_init(void) +{ + vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL); + if (!vmcoreinfo_data) { + pr_warn("Memory allocation for vmcoreinfo_data failed\n"); + return -ENOMEM; + } + + vmcoreinfo_note = alloc_pages_exact(VMCOREINFO_NOTE_SIZE, + GFP_KERNEL | __GFP_ZERO); + if (!vmcoreinfo_note) { + free_page((unsigned long)vmcoreinfo_data); + vmcoreinfo_data = NULL; + pr_warn("Memory allocation for vmcoreinfo_note failed\n"); + return -ENOMEM; + } + + VMCOREINFO_OSRELEASE(init_uts_ns.name.release); + VMCOREINFO_BUILD_ID(); + VMCOREINFO_PAGESIZE(PAGE_SIZE); + + VMCOREINFO_SYMBOL(init_uts_ns); + VMCOREINFO_OFFSET(uts_namespace, name); + VMCOREINFO_SYMBOL(node_online_map); +#ifdef CONFIG_MMU + VMCOREINFO_SYMBOL_ARRAY(swapper_pg_dir); +#endif + VMCOREINFO_SYMBOL(_stext); + vmcoreinfo_append_str("NUMBER(VMALLOC_START)=0x%lx\n", (unsigned long) VMALLOC_START); + +#ifndef CONFIG_NUMA + VMCOREINFO_SYMBOL(mem_map); + VMCOREINFO_SYMBOL(contig_page_data); +#endif +#ifdef CONFIG_SPARSEMEM_VMEMMAP + VMCOREINFO_SYMBOL_ARRAY(vmemmap); +#endif +#ifdef CONFIG_SPARSEMEM + VMCOREINFO_SYMBOL_ARRAY(mem_section); + VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS); + VMCOREINFO_STRUCT_SIZE(mem_section); + VMCOREINFO_OFFSET(mem_section, section_mem_map); + VMCOREINFO_NUMBER(SECTION_SIZE_BITS); + VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS); +#endif + VMCOREINFO_STRUCT_SIZE(page); + VMCOREINFO_STRUCT_SIZE(pglist_data); + VMCOREINFO_STRUCT_SIZE(zone); + VMCOREINFO_STRUCT_SIZE(free_area); + VMCOREINFO_STRUCT_SIZE(list_head); + VMCOREINFO_SIZE(nodemask_t); + VMCOREINFO_OFFSET(page, flags); + VMCOREINFO_OFFSET(page, _refcount); + VMCOREINFO_OFFSET(page, mapping); + VMCOREINFO_OFFSET(page, lru); + VMCOREINFO_OFFSET(page, _mapcount); + VMCOREINFO_OFFSET(page, private); + VMCOREINFO_OFFSET(page, compound_head); + VMCOREINFO_OFFSET(pglist_data, node_zones); + VMCOREINFO_OFFSET(pglist_data, nr_zones); +#ifdef CONFIG_FLATMEM + VMCOREINFO_OFFSET(pglist_data, node_mem_map); +#endif + VMCOREINFO_OFFSET(pglist_data, node_start_pfn); + VMCOREINFO_OFFSET(pglist_data, node_spanned_pages); + VMCOREINFO_OFFSET(pglist_data, node_id); + VMCOREINFO_OFFSET(zone, free_area); + VMCOREINFO_OFFSET(zone, vm_stat); + VMCOREINFO_OFFSET(zone, spanned_pages); + VMCOREINFO_OFFSET(free_area, free_list); + VMCOREINFO_OFFSET(list_head, next); + VMCOREINFO_OFFSET(list_head, prev); + VMCOREINFO_LENGTH(zone.free_area, NR_PAGE_ORDERS); + log_buf_vmcoreinfo_setup(); + VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES); + VMCOREINFO_NUMBER(NR_FREE_PAGES); + VMCOREINFO_NUMBER(PG_lru); + VMCOREINFO_NUMBER(PG_private); + VMCOREINFO_NUMBER(PG_swapcache); + VMCOREINFO_NUMBER(PG_swapbacked); + VMCOREINFO_NUMBER(PG_slab); +#ifdef CONFIG_MEMORY_FAILURE + VMCOREINFO_NUMBER(PG_hwpoison); +#endif + VMCOREINFO_NUMBER(PG_head_mask); +#define PAGE_BUDDY_MAPCOUNT_VALUE (~PG_buddy) + VMCOREINFO_NUMBER(PAGE_BUDDY_MAPCOUNT_VALUE); +#ifdef CONFIG_HUGETLB_PAGE + VMCOREINFO_NUMBER(PG_hugetlb); +#define PAGE_OFFLINE_MAPCOUNT_VALUE (~PG_offline) + VMCOREINFO_NUMBER(PAGE_OFFLINE_MAPCOUNT_VALUE); +#endif + +#ifdef CONFIG_KALLSYMS + VMCOREINFO_SYMBOL(kallsyms_names); + VMCOREINFO_SYMBOL(kallsyms_num_syms); + VMCOREINFO_SYMBOL(kallsyms_token_table); + VMCOREINFO_SYMBOL(kallsyms_token_index); +#ifdef CONFIG_KALLSYMS_BASE_RELATIVE + VMCOREINFO_SYMBOL(kallsyms_offsets); + VMCOREINFO_SYMBOL(kallsyms_relative_base); +#else + VMCOREINFO_SYMBOL(kallsyms_addresses); +#endif /* CONFIG_KALLSYMS_BASE_RELATIVE */ +#endif /* CONFIG_KALLSYMS */ + + arch_crash_save_vmcoreinfo(); + update_vmcoreinfo_note(); + + return 0; +} + +subsys_initcall(crash_save_vmcoreinfo_init); diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 81a8862295d6..d7b2125503af 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -796,8 +796,8 @@ static int proc_watchdog_common(int which, struct ctl_table *table, int write, /* * /proc/sys/kernel/watchdog */ -int proc_watchdog(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_watchdog(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(WATCHDOG_HARDLOCKUP_ENABLED | WATCHDOG_SOFTOCKUP_ENABLED, @@ -807,8 +807,8 @@ int proc_watchdog(struct ctl_table *table, int write, /* * /proc/sys/kernel/nmi_watchdog */ -int proc_nmi_watchdog(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_nmi_watchdog(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { if (!watchdog_hardlockup_available && write) return -ENOTSUPP; @@ -816,21 +816,23 @@ int proc_nmi_watchdog(struct ctl_table *table, int write, table, write, buffer, lenp, ppos); } +#ifdef CONFIG_SOFTLOCKUP_DETECTOR /* * /proc/sys/kernel/soft_watchdog */ -int proc_soft_watchdog(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_soft_watchdog(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(WATCHDOG_SOFTOCKUP_ENABLED, table, write, buffer, lenp, ppos); } +#endif /* * /proc/sys/kernel/watchdog_thresh */ -int proc_watchdog_thresh(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_watchdog_thresh(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int err, old; @@ -852,8 +854,8 @@ int proc_watchdog_thresh(struct ctl_table *table, int write, * user to specify a mask that will include cpus that have not yet * been brought online, if desired. */ -int proc_watchdog_cpumask(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) +static int proc_watchdog_cpumask(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int err; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 76e60faed892..bf2bdac46843 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -29,6 +29,7 @@ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> +#include <linux/interrupt.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> @@ -53,10 +54,11 @@ #include <linux/nmi.h> #include <linux/kvm_para.h> #include <linux/delay.h> +#include <linux/irq_work.h> #include "workqueue_internal.h" -enum { +enum worker_pool_flags { /* * worker_pool flags * @@ -72,10 +74,17 @@ enum { * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. + * + * As there can only be one concurrent BH execution context per CPU, a + * BH pool is per-CPU and always DISASSOCIATED. */ - POOL_MANAGER_ACTIVE = 1 << 0, /* being managed */ + POOL_BH = 1 << 0, /* is a BH pool */ + POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ + POOL_BH_DRAINING = 1 << 3, /* draining after CPU offline */ +}; +enum worker_flags { /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ @@ -86,7 +95,13 @@ enum { WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, +}; +enum work_cancel_flags { + WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */ +}; + +enum wq_internal_consts { NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ @@ -108,10 +123,18 @@ enum { RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, - WQ_NAME_LEN = 24, + WQ_NAME_LEN = 32, }; /* + * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and + * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because + * msecs_to_jiffies() can't be an initializer. + */ +#define BH_WORKER_JIFFIES msecs_to_jiffies(2) +#define BH_WORKER_RESTARTS 10 + +/* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for @@ -122,6 +145,9 @@ enum { * * L: pool->lock protected. Access with pool->lock held. * + * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for + * reads. + * * K: Only modified by worker while holding pool->lock. Can be safely read by * self, while holding pool->lock or from IRQ context if %current is the * kworker. @@ -143,6 +169,9 @@ enum { * * WR: wq->mutex protected for writes. RCU protected for reads. * + * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read + * with READ_ONCE() without locking. + * * MD: wq_mayday_lock protected. * * WD: Used internally by the watchdog. @@ -219,7 +248,7 @@ enum pool_workqueue_stats { }; /* - * The per-pool workqueue. While queued, the lower WORK_STRUCT_FLAG_BITS + * The per-pool workqueue. While queued, bits below WORK_PWQ_SHIFT * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. @@ -232,6 +261,7 @@ struct pool_workqueue { int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ + bool plugged; /* L: execution suspended */ /* * nr_active management and WORK_STRUCT_INACTIVE: @@ -240,18 +270,18 @@ struct pool_workqueue { * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * - * All work items marked with WORK_STRUCT_INACTIVE do not participate - * in pwq->nr_active and all work items in pwq->inactive_works are - * marked with WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE - * work items are in pwq->inactive_works. Some of them are ready to - * run in pool->worklist or worker->scheduled. Those work itmes are - * only struct wq_barrier which is used for flush_work() and should - * not participate in pwq->nr_active. For non-barrier work item, it - * is marked with WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. + * All work items marked with WORK_STRUCT_INACTIVE do not participate in + * nr_active and all work items in pwq->inactive_works are marked with + * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are + * in pwq->inactive_works. Some of them are ready to run in + * pool->worklist or worker->scheduled. Those work itmes are only struct + * wq_barrier which is used for flush_work() and should not participate + * in nr_active. For non-barrier work item, it is marked with + * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ - int max_active; /* L: max active works */ struct list_head inactive_works; /* L: inactive works */ + struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ @@ -265,7 +295,7 @@ struct pool_workqueue { */ struct kthread_work release_work; struct rcu_head rcu; -} __aligned(1 << WORK_STRUCT_FLAG_BITS); +} __aligned(1 << WORK_STRUCT_PWQ_SHIFT); /* * Structure used to wait for workqueue flush. @@ -279,6 +309,26 @@ struct wq_flusher { struct wq_device; /* + * Unlike in a per-cpu workqueue where max_active limits its concurrency level + * on each CPU, in an unbound workqueue, max_active applies to the whole system. + * As sharing a single nr_active across multiple sockets can be very expensive, + * the counting and enforcement is per NUMA node. + * + * The following struct is used to enforce per-node max_active. When a pwq wants + * to start executing a work item, it should increment ->nr using + * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over + * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish + * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in + * round-robin order. + */ +struct wq_node_nr_active { + int max; /* per-node max_active */ + atomic_t nr; /* per-node nr_active */ + raw_spinlock_t lock; /* nests inside pool locks */ + struct list_head pending_pwqs; /* LN: pwqs with inactive works */ +}; + +/* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ @@ -298,10 +348,15 @@ struct workqueue_struct { struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ - int saved_max_active; /* WQ: saved pwq max_active */ + + /* See alloc_workqueue() function comment for info on min/max_active */ + int max_active; /* WO: max active works */ + int min_active; /* WO: min active works */ + int saved_max_active; /* WQ: saved max_active */ + int saved_min_active; /* WQ: saved min_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ - struct pool_workqueue *dfl_pwq; /* PW: only for unbound wqs */ + struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ @@ -323,10 +378,9 @@ struct workqueue_struct { /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */ + struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; -static struct kmem_cache *pwq_cache; - /* * Each pod type describes how CPUs should be grouped for unbound workqueues. * See the comment above workqueue_attrs->affn_scope. @@ -338,16 +392,13 @@ struct wq_pod_type { int *cpu_pod; /* cpu -> pod */ }; -static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; -static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE; - static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { - [WQ_AFFN_DFL] = "default", - [WQ_AFFN_CPU] = "cpu", - [WQ_AFFN_SMT] = "smt", - [WQ_AFFN_CACHE] = "cache", - [WQ_AFFN_NUMA] = "numa", - [WQ_AFFN_SYSTEM] = "system", + [WQ_AFFN_DFL] = "default", + [WQ_AFFN_CPU] = "cpu", + [WQ_AFFN_SMT] = "smt", + [WQ_AFFN_CACHE] = "cache", + [WQ_AFFN_NUMA] = "numa", + [WQ_AFFN_SYSTEM] = "system", }; /* @@ -359,12 +410,22 @@ static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { */ static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); +#ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT +static unsigned int wq_cpu_intensive_warning_thresh = 4; +module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644); +#endif /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ +static bool wq_topo_initialized __read_mostly = false; + +static struct kmem_cache *pwq_cache; + +static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; +static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE; /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *wq_update_pod_attrs_buf; @@ -405,8 +466,17 @@ static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); +/* to raise softirq for the BH worker pools on other CPUs */ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS], + bh_pool_irq_works); + +/* the BH worker pools */ +static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], + bh_worker_pools); + /* the per-cpu worker pools */ -static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); +static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], + cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ @@ -420,6 +490,12 @@ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; /* + * Used to synchronize multiple cancel_sync attempts on the same work item. See + * work_grab_pending() and __cancel_work_sync(). + */ +static DECLARE_WAIT_QUEUE_HEAD(wq_cancel_waitq); + +/* * I: kthread_worker to release pwq's. pwq release needs to be bounced to a * process context while holding a pool lock. Bounce to a dedicated kthread * worker to avoid A-A deadlocks. @@ -440,6 +516,10 @@ struct workqueue_struct *system_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); +struct workqueue_struct *system_bh_wq; +EXPORT_SYMBOL_GPL(system_bh_wq); +struct workqueue_struct *system_bh_highpri_wq; +EXPORT_SYMBOL_GPL(system_bh_highpri_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); @@ -450,16 +530,21 @@ static void show_one_worker_pool(struct worker_pool *pool); #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ - RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ - RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") +#define for_each_bh_worker_pool(pool, cpu) \ + for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \ + (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ + (pool)++) + #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ @@ -632,6 +717,36 @@ static int worker_pool_assign_id(struct worker_pool *pool) return ret; } +static struct pool_workqueue __rcu ** +unbound_pwq_slot(struct workqueue_struct *wq, int cpu) +{ + if (cpu >= 0) + return per_cpu_ptr(wq->cpu_pwq, cpu); + else + return &wq->dfl_pwq; +} + +/* @cpu < 0 for dfl_pwq */ +static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu) +{ + return rcu_dereference_check(*unbound_pwq_slot(wq, cpu), + lockdep_is_held(&wq_pool_mutex) || + lockdep_is_held(&wq->mutex)); +} + +/** + * unbound_effective_cpumask - effective cpumask of an unbound workqueue + * @wq: workqueue of interest + * + * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which + * is masked with wq_unbound_cpumask to determine the effective cpumask. The + * default pwq is always mapped to the pool with the current effective cpumask. + */ +static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq) +{ + return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask; +} + static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; @@ -653,10 +768,9 @@ static int work_next_color(int color) * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * - * set_work_pwq(), set_work_pool_and_clear_pending(), mark_work_canceling() - * and clear_work_data() can be used to set the pwq, pool or clear - * work->data. These functions should only be called while the work is - * owned - ie. while the PENDING bit is set. + * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling() + * can be used to set the pwq, pool or clear work->data. These functions should + * only be called while the work is owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been @@ -668,29 +782,28 @@ static int work_next_color(int color) * but stay off timer and worklist for arbitrarily long and nobody should * try to steal the PENDING bit. */ -static inline void set_work_data(struct work_struct *work, unsigned long data, - unsigned long flags) +static inline void set_work_data(struct work_struct *work, unsigned long data) { WARN_ON_ONCE(!work_pending(work)); - atomic_long_set(&work->data, data | flags | work_static(work)); + atomic_long_set(&work->data, data | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, - unsigned long extra_flags) + unsigned long flags) { - set_work_data(work, (unsigned long)pwq, - WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | extra_flags); + set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING | + WORK_STRUCT_PWQ | flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, - int pool_id) + int pool_id, unsigned long flags) { - set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, - WORK_STRUCT_PENDING); + set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | + WORK_STRUCT_PENDING | flags); } static void set_work_pool_and_clear_pending(struct work_struct *work, - int pool_id) + int pool_id, unsigned long flags) { /* * The following wmb is paired with the implied mb in @@ -699,7 +812,8 @@ static void set_work_pool_and_clear_pending(struct work_struct *work, * owner. */ smp_wmb(); - set_work_data(work, (unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT, 0); + set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | + flags); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from @@ -731,15 +845,9 @@ static void set_work_pool_and_clear_pending(struct work_struct *work, smp_mb(); } -static void clear_work_data(struct work_struct *work) -{ - smp_wmb(); /* see set_work_pool_and_clear_pending() */ - set_work_data(work, WORK_STRUCT_NO_POOL, 0); -} - static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { - return (struct pool_workqueue *)(data & WORK_STRUCT_WQ_DATA_MASK); + return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) @@ -806,7 +914,7 @@ static void mark_work_canceling(struct work_struct *work) unsigned long pool_id = get_work_pool_id(work); pool_id <<= WORK_OFFQ_POOL_SHIFT; - set_work_data(work, pool_id | WORK_OFFQ_CANCELING, WORK_STRUCT_PENDING); + set_work_data(work, pool_id | WORK_STRUCT_PENDING | WORK_OFFQ_CANCELING); } static bool work_is_canceling(struct work_struct *work) @@ -1101,6 +1209,29 @@ static bool assign_work(struct work_struct *work, struct worker *worker, return true; } +static struct irq_work *bh_pool_irq_work(struct worker_pool *pool) +{ + int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0; + + return &per_cpu(bh_pool_irq_works, pool->cpu)[high]; +} + +static void kick_bh_pool(struct worker_pool *pool) +{ +#ifdef CONFIG_SMP + /* see drain_dead_softirq_workfn() for BH_DRAINING */ + if (unlikely(pool->cpu != smp_processor_id() && + !(pool->flags & POOL_BH_DRAINING))) { + irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu); + return; + } +#endif + if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) + raise_softirq_irqoff(HI_SOFTIRQ); + else + raise_softirq_irqoff(TASKLET_SOFTIRQ); +} + /** * kick_pool - wake up an idle worker if necessary * @pool: pool to kick @@ -1118,6 +1249,11 @@ static bool kick_pool(struct worker_pool *pool) if (!need_more_worker(pool) || !worker) return false; + if (pool->flags & POOL_BH) { + kick_bh_pool(pool); + return true; + } + p = worker->task; #ifdef CONFIG_SMP @@ -1198,11 +1334,13 @@ restart: u64 cnt; /* - * Start reporting from the fourth time and back off + * Start reporting from the warning_thresh and back off * exponentially. */ cnt = atomic64_inc_return_relaxed(&ent->cnt); - if (cnt >= 4 && is_power_of_2(cnt)) + if (wq_cpu_intensive_warning_thresh && + cnt >= wq_cpu_intensive_warning_thresh && + is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh)) printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n", ent->func, wq_cpu_intensive_thresh_us, atomic64_read(&ent->cnt)); @@ -1231,10 +1369,12 @@ restart: ent = &wci_ents[wci_nr_ents++]; ent->func = func; - atomic64_set(&ent->cnt, 1); + atomic64_set(&ent->cnt, 0); hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func); raw_spin_unlock(&wci_lock); + + goto restart; } #else /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ @@ -1402,6 +1542,74 @@ work_func_t wq_worker_last_func(struct task_struct *task) } /** + * wq_node_nr_active - Determine wq_node_nr_active to use + * @wq: workqueue of interest + * @node: NUMA node, can be %NUMA_NO_NODE + * + * Determine wq_node_nr_active to use for @wq on @node. Returns: + * + * - %NULL for per-cpu workqueues as they don't need to use shared nr_active. + * + * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE. + * + * - Otherwise, node_nr_active[@node]. + */ +static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq, + int node) +{ + if (!(wq->flags & WQ_UNBOUND)) + return NULL; + + if (node == NUMA_NO_NODE) + node = nr_node_ids; + + return wq->node_nr_active[node]; +} + +/** + * wq_update_node_max_active - Update per-node max_actives to use + * @wq: workqueue to update + * @off_cpu: CPU that's going down, -1 if a CPU is not going down + * + * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is + * distributed among nodes according to the proportions of numbers of online + * cpus. The result is always between @wq->min_active and max_active. + */ +static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) +{ + struct cpumask *effective = unbound_effective_cpumask(wq); + int min_active = READ_ONCE(wq->min_active); + int max_active = READ_ONCE(wq->max_active); + int total_cpus, node; + + lockdep_assert_held(&wq->mutex); + + if (!wq_topo_initialized) + return; + + if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective)) + off_cpu = -1; + + total_cpus = cpumask_weight_and(effective, cpu_online_mask); + if (off_cpu >= 0) + total_cpus--; + + for_each_node(node) { + int node_cpus; + + node_cpus = cpumask_weight_and(effective, cpumask_of_node(node)); + if (off_cpu >= 0 && cpu_to_node(off_cpu) == node) + node_cpus--; + + wq_node_nr_active(wq, node)->max = + clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus), + min_active, max_active); + } + + wq_node_nr_active(wq, NUMA_NO_NODE)->max = min_active; +} + +/** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * @@ -1453,24 +1661,336 @@ static void put_pwq_unlocked(struct pool_workqueue *pwq) } } -static void pwq_activate_inactive_work(struct work_struct *work) +static bool pwq_is_empty(struct pool_workqueue *pwq) { - struct pool_workqueue *pwq = get_work_pwq(work); + return !pwq->nr_active && list_empty(&pwq->inactive_works); +} +static void __pwq_activate_work(struct pool_workqueue *pwq, + struct work_struct *work) +{ + unsigned long *wdb = work_data_bits(work); + + WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); - __clear_bit(WORK_STRUCT_INACTIVE_BIT, work_data_bits(work)); + __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); +} + +/** + * pwq_activate_work - Activate a work item if inactive + * @pwq: pool_workqueue @work belongs to + * @work: work item to activate + * + * Returns %true if activated. %false if already active. + */ +static bool pwq_activate_work(struct pool_workqueue *pwq, + struct work_struct *work) +{ + struct worker_pool *pool = pwq->pool; + struct wq_node_nr_active *nna; + + lockdep_assert_held(&pool->lock); + + if (!(*work_data_bits(work) & WORK_STRUCT_INACTIVE)) + return false; + + nna = wq_node_nr_active(pwq->wq, pool->node); + if (nna) + atomic_inc(&nna->nr); + pwq->nr_active++; + __pwq_activate_work(pwq, work); + return true; +} + +static bool tryinc_node_nr_active(struct wq_node_nr_active *nna) +{ + int max = READ_ONCE(nna->max); + + while (true) { + int old, tmp; + + old = atomic_read(&nna->nr); + if (old >= max) + return false; + tmp = atomic_cmpxchg_relaxed(&nna->nr, old, old + 1); + if (tmp == old) + return true; + } +} + +/** + * pwq_tryinc_nr_active - Try to increment nr_active for a pwq + * @pwq: pool_workqueue of interest + * @fill: max_active may have increased, try to increase concurrency level + * + * Try to increment nr_active for @pwq. Returns %true if an nr_active count is + * successfully obtained. %false otherwise. + */ +static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) +{ + struct workqueue_struct *wq = pwq->wq; + struct worker_pool *pool = pwq->pool; + struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node); + bool obtained = false; + + lockdep_assert_held(&pool->lock); + + if (!nna) { + /* BH or per-cpu workqueue, pwq->nr_active is sufficient */ + obtained = pwq->nr_active < READ_ONCE(wq->max_active); + goto out; + } + + if (unlikely(pwq->plugged)) + return false; + + /* + * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is + * already waiting on $nna, pwq_dec_nr_active() will maintain the + * concurrency level. Don't jump the line. + * + * We need to ignore the pending test after max_active has increased as + * pwq_dec_nr_active() can only maintain the concurrency level but not + * increase it. This is indicated by @fill. + */ + if (!list_empty(&pwq->pending_node) && likely(!fill)) + goto out; + + obtained = tryinc_node_nr_active(nna); + if (obtained) + goto out; + + /* + * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs + * and try again. The smp_mb() is paired with the implied memory barrier + * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either + * we see the decremented $nna->nr or they see non-empty + * $nna->pending_pwqs. + */ + raw_spin_lock(&nna->lock); + + if (list_empty(&pwq->pending_node)) + list_add_tail(&pwq->pending_node, &nna->pending_pwqs); + else if (likely(!fill)) + goto out_unlock; + + smp_mb(); + + obtained = tryinc_node_nr_active(nna); + + /* + * If @fill, @pwq might have already been pending. Being spuriously + * pending in cold paths doesn't affect anything. Let's leave it be. + */ + if (obtained && likely(!fill)) + list_del_init(&pwq->pending_node); + +out_unlock: + raw_spin_unlock(&nna->lock); +out: + if (obtained) + pwq->nr_active++; + return obtained; +} + +/** + * pwq_activate_first_inactive - Activate the first inactive work item on a pwq + * @pwq: pool_workqueue of interest + * @fill: max_active may have increased, try to increase concurrency level + * + * Activate the first inactive work item of @pwq if available and allowed by + * max_active limit. + * + * Returns %true if an inactive work item has been activated. %false if no + * inactive work item is found or max_active limit is reached. + */ +static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill) +{ + struct work_struct *work = + list_first_entry_or_null(&pwq->inactive_works, + struct work_struct, entry); + + if (work && pwq_tryinc_nr_active(pwq, fill)) { + __pwq_activate_work(pwq, work); + return true; + } else { + return false; + } } -static void pwq_activate_first_inactive(struct pool_workqueue *pwq) +/** + * unplug_oldest_pwq - unplug the oldest pool_workqueue + * @wq: workqueue_struct where its oldest pwq is to be unplugged + * + * This function should only be called for ordered workqueues where only the + * oldest pwq is unplugged, the others are plugged to suspend execution to + * ensure proper work item ordering:: + * + * dfl_pwq --------------+ [P] - plugged + * | + * v + * pwqs -> A -> B [P] -> C [P] (newest) + * | | | + * 1 3 5 + * | | | + * 2 4 6 + * + * When the oldest pwq is drained and removed, this function should be called + * to unplug the next oldest one to start its work item execution. Note that + * pwq's are linked into wq->pwqs with the oldest first, so the first one in + * the list is the oldest. + */ +static void unplug_oldest_pwq(struct workqueue_struct *wq) { - struct work_struct *work = list_first_entry(&pwq->inactive_works, - struct work_struct, entry); + struct pool_workqueue *pwq; - pwq_activate_inactive_work(work); + lockdep_assert_held(&wq->mutex); + + /* Caller should make sure that pwqs isn't empty before calling */ + pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue, + pwqs_node); + raw_spin_lock_irq(&pwq->pool->lock); + if (pwq->plugged) { + pwq->plugged = false; + if (pwq_activate_first_inactive(pwq, true)) + kick_pool(pwq->pool); + } + raw_spin_unlock_irq(&pwq->pool->lock); +} + +/** + * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active + * @nna: wq_node_nr_active to activate a pending pwq for + * @caller_pool: worker_pool the caller is locking + * + * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked. + * @caller_pool may be unlocked and relocked to lock other worker_pools. + */ +static void node_activate_pending_pwq(struct wq_node_nr_active *nna, + struct worker_pool *caller_pool) +{ + struct worker_pool *locked_pool = caller_pool; + struct pool_workqueue *pwq; + struct work_struct *work; + + lockdep_assert_held(&caller_pool->lock); + + raw_spin_lock(&nna->lock); +retry: + pwq = list_first_entry_or_null(&nna->pending_pwqs, + struct pool_workqueue, pending_node); + if (!pwq) + goto out_unlock; + + /* + * If @pwq is for a different pool than @locked_pool, we need to lock + * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock + * / lock dance. For that, we also need to release @nna->lock as it's + * nested inside pool locks. + */ + if (pwq->pool != locked_pool) { + raw_spin_unlock(&locked_pool->lock); + locked_pool = pwq->pool; + if (!raw_spin_trylock(&locked_pool->lock)) { + raw_spin_unlock(&nna->lock); + raw_spin_lock(&locked_pool->lock); + raw_spin_lock(&nna->lock); + goto retry; + } + } + + /* + * $pwq may not have any inactive work items due to e.g. cancellations. + * Drop it from pending_pwqs and see if there's another one. + */ + work = list_first_entry_or_null(&pwq->inactive_works, + struct work_struct, entry); + if (!work) { + list_del_init(&pwq->pending_node); + goto retry; + } + + /* + * Acquire an nr_active count and activate the inactive work item. If + * $pwq still has inactive work items, rotate it to the end of the + * pending_pwqs so that we round-robin through them. This means that + * inactive work items are not activated in queueing order which is fine + * given that there has never been any ordering across different pwqs. + */ + if (likely(tryinc_node_nr_active(nna))) { + pwq->nr_active++; + __pwq_activate_work(pwq, work); + + if (list_empty(&pwq->inactive_works)) + list_del_init(&pwq->pending_node); + else + list_move_tail(&pwq->pending_node, &nna->pending_pwqs); + + /* if activating a foreign pool, make sure it's running */ + if (pwq->pool != caller_pool) + kick_pool(pwq->pool); + } + +out_unlock: + raw_spin_unlock(&nna->lock); + if (locked_pool != caller_pool) { + raw_spin_unlock(&locked_pool->lock); + raw_spin_lock(&caller_pool->lock); + } +} + +/** + * pwq_dec_nr_active - Retire an active count + * @pwq: pool_workqueue of interest + * + * Decrement @pwq's nr_active and try to activate the first inactive work item. + * For unbound workqueues, this function may temporarily drop @pwq->pool->lock. + */ +static void pwq_dec_nr_active(struct pool_workqueue *pwq) +{ + struct worker_pool *pool = pwq->pool; + struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node); + + lockdep_assert_held(&pool->lock); + + /* + * @pwq->nr_active should be decremented for both percpu and unbound + * workqueues. + */ + pwq->nr_active--; + + /* + * For a percpu workqueue, it's simple. Just need to kick the first + * inactive work item on @pwq itself. + */ + if (!nna) { + pwq_activate_first_inactive(pwq, false); + return; + } + + /* + * If @pwq is for an unbound workqueue, it's more complicated because + * multiple pwqs and pools may be sharing the nr_active count. When a + * pwq needs to wait for an nr_active count, it puts itself on + * $nna->pending_pwqs. The following atomic_dec_return()'s implied + * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to + * guarantee that either we see non-empty pending_pwqs or they see + * decremented $nna->nr. + * + * $nna->max may change as CPUs come online/offline and @pwq->wq's + * max_active gets updated. However, it is guaranteed to be equal to or + * larger than @pwq->wq->min_active which is above zero unless freezing. + * This maintains the forward progress guarantee. + */ + if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max)) + return; + + if (!list_empty(&nna->pending_pwqs)) + node_activate_pending_pwq(nna, pool); } /** @@ -1481,6 +2001,11 @@ static void pwq_activate_first_inactive(struct pool_workqueue *pwq) * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * + * NOTE: + * For unbound workqueues, this function may temporarily drop @pwq->pool->lock + * and thus should be called after all other state updates for the in-flight + * work item is complete. + * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ @@ -1488,14 +2013,8 @@ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_ { int color = get_work_color(work_data); - if (!(work_data & WORK_STRUCT_INACTIVE)) { - pwq->nr_active--; - if (!list_empty(&pwq->inactive_works)) { - /* one down, submit an inactive one */ - if (pwq->nr_active < pwq->max_active) - pwq_activate_first_inactive(pwq); - } - } + if (!(work_data & WORK_STRUCT_INACTIVE)) + pwq_dec_nr_active(pwq); pwq->nr_in_flight[color]--; @@ -1523,8 +2042,8 @@ out_put: /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal - * @is_dwork: @work is a delayed_work - * @flags: place to store irq state + * @cflags: %WORK_CANCEL_ flags + * @irq_flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. @@ -1546,20 +2065,20 @@ out_put: * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is - * responsible for releasing it using local_irq_restore(*@flags). + * responsible for releasing it using local_irq_restore(*@irq_flags). * * This function is safe to call from any context including IRQ handler. */ -static int try_to_grab_pending(struct work_struct *work, bool is_dwork, - unsigned long *flags) +static int try_to_grab_pending(struct work_struct *work, u32 cflags, + unsigned long *irq_flags) { struct worker_pool *pool; struct pool_workqueue *pwq; - local_irq_save(*flags); + local_irq_save(*irq_flags); /* try to steal the timer if it exists */ - if (is_dwork) { + if (cflags & WORK_CANCEL_DELAYED) { struct delayed_work *dwork = to_delayed_work(work); /* @@ -1595,6 +2114,8 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { + unsigned long work_data; + debug_work_deactivate(work); /* @@ -1608,14 +2129,19 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, * management later on and cause stall. Make sure the work * item is activated before grabbing. */ - if (*work_data_bits(work) & WORK_STRUCT_INACTIVE) - pwq_activate_inactive_work(work); + pwq_activate_work(pwq, work); list_del_init(&work->entry); - pwq_dec_nr_in_flight(pwq, *work_data_bits(work)); - /* work->data points to pwq iff queued, point to pool */ - set_work_pool_and_keep_pending(work, pool->id); + /* + * work->data points to pwq iff queued. Let's point to pool. As + * this destroys work->data needed by the next step, stash it. + */ + work_data = *work_data_bits(work); + set_work_pool_and_keep_pending(work, pool->id, 0); + + /* must be the last step, see the function comment */ + pwq_dec_nr_in_flight(pwq, work_data); raw_spin_unlock(&pool->lock); rcu_read_unlock(); @@ -1624,13 +2150,82 @@ static int try_to_grab_pending(struct work_struct *work, bool is_dwork, raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); - local_irq_restore(*flags); + local_irq_restore(*irq_flags); if (work_is_canceling(work)) return -ENOENT; cpu_relax(); return -EAGAIN; } +struct cwt_wait { + wait_queue_entry_t wait; + struct work_struct *work; +}; + +static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) +{ + struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); + + if (cwait->work != key) + return 0; + return autoremove_wake_function(wait, mode, sync, key); +} + +/** + * work_grab_pending - steal work item from worklist and disable irq + * @work: work item to steal + * @cflags: %WORK_CANCEL_ flags + * @irq_flags: place to store IRQ state + * + * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer + * or on worklist. + * + * Must be called in process context. IRQ is disabled on return with IRQ state + * stored in *@irq_flags. The caller is responsible for re-enabling it using + * local_irq_restore(). + * + * Returns %true if @work was pending. %false if idle. + */ +static bool work_grab_pending(struct work_struct *work, u32 cflags, + unsigned long *irq_flags) +{ + struct cwt_wait cwait; + int ret; + + might_sleep(); +repeat: + ret = try_to_grab_pending(work, cflags, irq_flags); + if (likely(ret >= 0)) + return ret; + if (ret != -ENOENT) + goto repeat; + + /* + * Someone is already canceling. Wait for it to finish. flush_work() + * doesn't work for PREEMPT_NONE because we may get woken up between + * @work's completion and the other canceling task resuming and clearing + * CANCELING - flush_work() will return false immediately as @work is no + * longer busy, try_to_grab_pending() will return -ENOENT as @work is + * still being canceled and the other canceling task won't be able to + * clear CANCELING as we're hogging the CPU. + * + * Let's wait for completion using a waitqueue. As this may lead to the + * thundering herd problem, use a custom wake function which matches + * @work along with exclusive wait and wakeup. + */ + init_wait(&cwait.wait); + cwait.wait.func = cwt_wakefn; + cwait.work = work; + + prepare_to_wait_exclusive(&wq_cancel_waitq, &cwait.wait, + TASK_UNINTERRUPTIBLE); + if (work_is_canceling(work)) + schedule(); + finish_wait(&wq_cancel_waitq, &cwait.wait); + + goto repeat; +} + /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to @@ -1718,7 +2313,6 @@ static void __queue_work(int cpu, struct workqueue_struct *wq, */ lockdep_assert_irqs_disabled(); - /* * For a draining wq, only works from the same workqueue are * allowed. The __WQ_DESTROYING helps to spot the issue that @@ -1793,12 +2387,16 @@ retry: pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); - if (likely(pwq->nr_active < pwq->max_active)) { + /* + * Limit the number of concurrently active work items to max_active. + * @work must also queue behind existing inactive work items to maintain + * ordering when max_active changes. See wq_adjust_max_active(). + */ + if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) pool->watchdog_ts = jiffies; trace_workqueue_activate_work(work); - pwq->nr_active++; insert_work(pwq, work, &pool->worklist, work_flags); kick_pool(pool); } else { @@ -1829,16 +2427,16 @@ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; - unsigned long flags; + unsigned long irq_flags; - local_irq_save(flags); + local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_work(cpu, wq, work); ret = true; } - local_irq_restore(flags); + local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_work_on); @@ -1895,7 +2493,7 @@ static int select_numa_node_cpu(int node) bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { - unsigned long flags; + unsigned long irq_flags; bool ret = false; /* @@ -1909,7 +2507,7 @@ bool queue_work_node(int node, struct workqueue_struct *wq, */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); - local_irq_save(flags); + local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { int cpu = select_numa_node_cpu(node); @@ -1918,7 +2516,7 @@ bool queue_work_node(int node, struct workqueue_struct *wq, ret = true; } - local_irq_restore(flags); + local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); @@ -1958,10 +2556,18 @@ static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, dwork->cpu = cpu; timer->expires = jiffies + delay; - if (unlikely(cpu != WORK_CPU_UNBOUND)) + if (housekeeping_enabled(HK_TYPE_TIMER)) { + /* If the current cpu is a housekeeping cpu, use it. */ + cpu = smp_processor_id(); + if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER)) + cpu = housekeeping_any_cpu(HK_TYPE_TIMER); add_timer_on(timer, cpu); - else - add_timer(timer); + } else { + if (likely(cpu == WORK_CPU_UNBOUND)) + add_timer_global(timer); + else + add_timer_on(timer, cpu); + } } /** @@ -1980,17 +2586,17 @@ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, { struct work_struct *work = &dwork->work; bool ret = false; - unsigned long flags; + unsigned long irq_flags; /* read the comment in __queue_work() */ - local_irq_save(flags); + local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } - local_irq_restore(flags); + local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); @@ -2016,16 +2622,17 @@ EXPORT_SYMBOL(queue_delayed_work_on); bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { - unsigned long flags; + unsigned long irq_flags; int ret; do { - ret = try_to_grab_pending(&dwork->work, true, &flags); + ret = try_to_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, + &irq_flags); } while (unlikely(ret == -EAGAIN)); if (likely(ret >= 0)) { __queue_delayed_work(cpu, wq, dwork, delay); - local_irq_restore(flags); + local_irq_restore(irq_flags); } /* -ENOENT from try_to_grab_pending() becomes %true */ @@ -2100,19 +2707,21 @@ static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, - struct worker_pool *pool) + struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* - * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains - * stable across this function. See the comments above the flag - * definition for details. + * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable + * across this function. See the comments above the flag definition for + * details. BH workers are, while per-CPU, always DISASSOCIATED. */ - if (pool->flags & POOL_DISASSOCIATED) + if (pool->flags & POOL_DISASSOCIATED) { worker->flags |= WORKER_UNBOUND; - else + } else { + WARN_ON_ONCE(pool->flags & POOL_BH); kthread_set_per_cpu(worker->task, pool->cpu); + } if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); @@ -2136,6 +2745,9 @@ static void worker_detach_from_pool(struct worker *worker) struct worker_pool *pool = worker->pool; struct completion *detach_completion = NULL; + /* there is one permanent BH worker per CPU which should never detach */ + WARN_ON_ONCE(pool->flags & POOL_BH); + mutex_lock(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); @@ -2187,27 +2799,29 @@ static struct worker *create_worker(struct worker_pool *pool) worker->id = id; - if (pool->cpu >= 0) - snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, - pool->attrs->nice < 0 ? "H" : ""); - else - snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); - - worker->task = kthread_create_on_node(worker_thread, worker, pool->node, - "kworker/%s", id_buf); - if (IS_ERR(worker->task)) { - if (PTR_ERR(worker->task) == -EINTR) { - pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n", - id_buf); - } else { - pr_err_once("workqueue: Failed to create a worker thread: %pe", - worker->task); + if (!(pool->flags & POOL_BH)) { + if (pool->cpu >= 0) + snprintf(id_buf, sizeof(id_buf), "%d:%d%s", pool->cpu, id, + pool->attrs->nice < 0 ? "H" : ""); + else + snprintf(id_buf, sizeof(id_buf), "u%d:%d", pool->id, id); + + worker->task = kthread_create_on_node(worker_thread, worker, + pool->node, "kworker/%s", id_buf); + if (IS_ERR(worker->task)) { + if (PTR_ERR(worker->task) == -EINTR) { + pr_err("workqueue: Interrupted when creating a worker thread \"kworker/%s\"\n", + id_buf); + } else { + pr_err_once("workqueue: Failed to create a worker thread: %pe", + worker->task); + } + goto fail; } - goto fail; - } - set_user_nice(worker->task, pool->attrs->nice); - kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); + set_user_nice(worker->task, pool->attrs->nice); + kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); + } /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); @@ -2217,14 +2831,14 @@ static struct worker *create_worker(struct worker_pool *pool) worker->pool->nr_workers++; worker_enter_idle(worker); - kick_pool(pool); /* * @worker is waiting on a completion in kthread() and will trigger hung - * check if not woken up soon. As kick_pool() might not have waken it - * up, wake it up explicitly once more. + * check if not woken up soon. As kick_pool() is noop if @pool is empty, + * wake it up explicitly. */ - wake_up_process(worker->task); + if (worker->task) + wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); @@ -2543,6 +3157,8 @@ __acquires(&pool->lock) struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; unsigned long work_data; + int lockdep_start_depth, rcu_start_depth; + bool bh_draining = pool->flags & POOL_BH_DRAINING; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from @@ -2565,7 +3181,8 @@ __acquires(&pool->lock) worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; - worker->current_at = worker->task->se.sum_exec_runtime; + if (worker->task) + worker->current_at = worker->task->se.sum_exec_runtime; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); @@ -2600,12 +3217,16 @@ __acquires(&pool->lock) * PENDING and queued state changes happen together while IRQ is * disabled. */ - set_work_pool_and_clear_pending(work, pool->id); + set_work_pool_and_clear_pending(work, pool->id, 0); pwq->stats[PWQ_STAT_STARTED]++; raw_spin_unlock_irq(&pool->lock); - lock_map_acquire(&pwq->wq->lockdep_map); + rcu_start_depth = rcu_preempt_depth(); + lockdep_start_depth = lockdep_depth(current); + /* see drain_dead_softirq_workfn() */ + if (!bh_draining) + lock_map_acquire(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding @@ -2638,12 +3259,17 @@ __acquires(&pool->lock) trace_workqueue_execute_end(work, worker->current_func); pwq->stats[PWQ_STAT_COMPLETED]++; lock_map_release(&lockdep_map); - lock_map_release(&pwq->wq->lockdep_map); + if (!bh_draining) + lock_map_release(&pwq->wq->lockdep_map); - if (unlikely(in_atomic() || lockdep_depth(current) > 0)) { - pr_err("BUG: workqueue leaked lock or atomic: %s/0x%08x/%d\n" - " last function: %ps\n", - current->comm, preempt_count(), task_pid_nr(current), + if (unlikely((worker->task && in_atomic()) || + lockdep_depth(current) != lockdep_start_depth || + rcu_preempt_depth() != rcu_start_depth)) { + pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n" + " preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n", + current->comm, task_pid_nr(current), preempt_count(), + lockdep_start_depth, lockdep_depth(current), + rcu_start_depth, rcu_preempt_depth(), worker->current_func); debug_show_held_locks(current); dump_stack(); @@ -2657,7 +3283,8 @@ __acquires(&pool->lock) * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ - cond_resched(); + if (worker->task) + cond_resched(); raw_spin_lock_irq(&pool->lock); @@ -2677,6 +3304,8 @@ __acquires(&pool->lock) worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; + + /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); } @@ -2938,6 +3567,139 @@ repeat: goto repeat; } +static void bh_worker(struct worker *worker) +{ + struct worker_pool *pool = worker->pool; + int nr_restarts = BH_WORKER_RESTARTS; + unsigned long end = jiffies + BH_WORKER_JIFFIES; + + raw_spin_lock_irq(&pool->lock); + worker_leave_idle(worker); + + /* + * This function follows the structure of worker_thread(). See there for + * explanations on each step. + */ + if (!need_more_worker(pool)) + goto done; + + WARN_ON_ONCE(!list_empty(&worker->scheduled)); + worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); + + do { + struct work_struct *work = + list_first_entry(&pool->worklist, + struct work_struct, entry); + + if (assign_work(work, worker, NULL)) + process_scheduled_works(worker); + } while (keep_working(pool) && + --nr_restarts && time_before(jiffies, end)); + + worker_set_flags(worker, WORKER_PREP); +done: + worker_enter_idle(worker); + kick_pool(pool); + raw_spin_unlock_irq(&pool->lock); +} + +/* + * TODO: Convert all tasklet users to workqueue and use softirq directly. + * + * This is currently called from tasklet[_hi]action() and thus is also called + * whenever there are tasklets to run. Let's do an early exit if there's nothing + * queued. Once conversion from tasklet is complete, the need_more_worker() test + * can be dropped. + * + * After full conversion, we'll add worker->softirq_action, directly use the + * softirq action and obtain the worker pointer from the softirq_action pointer. + */ +void workqueue_softirq_action(bool highpri) +{ + struct worker_pool *pool = + &per_cpu(bh_worker_pools, smp_processor_id())[highpri]; + if (need_more_worker(pool)) + bh_worker(list_first_entry(&pool->workers, struct worker, node)); +} + +struct wq_drain_dead_softirq_work { + struct work_struct work; + struct worker_pool *pool; + struct completion done; +}; + +static void drain_dead_softirq_workfn(struct work_struct *work) +{ + struct wq_drain_dead_softirq_work *dead_work = + container_of(work, struct wq_drain_dead_softirq_work, work); + struct worker_pool *pool = dead_work->pool; + bool repeat; + + /* + * @pool's CPU is dead and we want to execute its still pending work + * items from this BH work item which is running on a different CPU. As + * its CPU is dead, @pool can't be kicked and, as work execution path + * will be nested, a lockdep annotation needs to be suppressed. Mark + * @pool with %POOL_BH_DRAINING for the special treatments. + */ + raw_spin_lock_irq(&pool->lock); + pool->flags |= POOL_BH_DRAINING; + raw_spin_unlock_irq(&pool->lock); + + bh_worker(list_first_entry(&pool->workers, struct worker, node)); + + raw_spin_lock_irq(&pool->lock); + pool->flags &= ~POOL_BH_DRAINING; + repeat = need_more_worker(pool); + raw_spin_unlock_irq(&pool->lock); + + /* + * bh_worker() might hit consecutive execution limit and bail. If there + * still are pending work items, reschedule self and return so that we + * don't hog this CPU's BH. + */ + if (repeat) { + if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) + queue_work(system_bh_highpri_wq, work); + else + queue_work(system_bh_wq, work); + } else { + complete(&dead_work->done); + } +} + +/* + * @cpu is dead. Drain the remaining BH work items on the current CPU. It's + * possible to allocate dead_work per CPU and avoid flushing. However, then we + * have to worry about draining overlapping with CPU coming back online or + * nesting (one CPU's dead_work queued on another CPU which is also dead and so + * on). Let's keep it simple and drain them synchronously. These are BH work + * items which shouldn't be requeued on the same pool. Shouldn't take long. + */ +void workqueue_softirq_dead(unsigned int cpu) +{ + int i; + + for (i = 0; i < NR_STD_WORKER_POOLS; i++) { + struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i]; + struct wq_drain_dead_softirq_work dead_work; + + if (!need_more_worker(pool)) + continue; + + INIT_WORK(&dead_work.work, drain_dead_softirq_workfn); + dead_work.pool = pool; + init_completion(&dead_work.done); + + if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) + queue_work(system_bh_highpri_wq, &dead_work.work); + else + queue_work(system_bh_wq, &dead_work.work); + + wait_for_completion(&dead_work.done); + } +} + /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed @@ -3010,6 +3772,7 @@ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { + static __maybe_unused struct lock_class_key bh_key, thr_key; unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; @@ -3019,15 +3782,20 @@ static void insert_wq_barrier(struct pool_workqueue *pwq, * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. + * + * BH and threaded workqueues need separate lockdep keys to avoid + * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} + * usage". */ - INIT_WORK_ONSTACK(&barr->work, wq_barrier_func); + INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func, + (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; - /* The barrier work item does not participate in pwq->nr_active. */ + /* The barrier work item does not participate in nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* @@ -3124,6 +3892,35 @@ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, return wait; } +static void touch_wq_lockdep_map(struct workqueue_struct *wq) +{ +#ifdef CONFIG_LOCKDEP + if (wq->flags & WQ_BH) + local_bh_disable(); + + lock_map_acquire(&wq->lockdep_map); + lock_map_release(&wq->lockdep_map); + + if (wq->flags & WQ_BH) + local_bh_enable(); +#endif +} + +static void touch_work_lockdep_map(struct work_struct *work, + struct workqueue_struct *wq) +{ +#ifdef CONFIG_LOCKDEP + if (wq->flags & WQ_BH) + local_bh_disable(); + + lock_map_acquire(&work->lockdep_map); + lock_map_release(&work->lockdep_map); + + if (wq->flags & WQ_BH) + local_bh_enable(); +#endif +} + /** * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush @@ -3143,8 +3940,7 @@ void __flush_workqueue(struct workqueue_struct *wq) if (WARN_ON(!wq_online)) return; - lock_map_acquire(&wq->lockdep_map); - lock_map_release(&wq->lockdep_map); + touch_wq_lockdep_map(wq); mutex_lock(&wq->mutex); @@ -3316,7 +4112,7 @@ reflush: bool drained; raw_spin_lock_irq(&pwq->pool->lock); - drained = !pwq->nr_active && list_empty(&pwq->inactive_works); + drained = pwq_is_empty(pwq); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) @@ -3343,6 +4139,7 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; + struct workqueue_struct *wq; might_sleep(); @@ -3366,11 +4163,14 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, pwq = worker->current_pwq; } - check_flush_dependency(pwq->wq, work); + wq = pwq->wq; + check_flush_dependency(wq, work); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); + touch_work_lockdep_map(work, wq); + /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. @@ -3380,11 +4180,9 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ - if (!from_cancel && - (pwq->wq->saved_max_active == 1 || pwq->wq->rescuer)) { - lock_map_acquire(&pwq->wq->lockdep_map); - lock_map_release(&pwq->wq->lockdep_map); - } + if (!from_cancel && (wq->saved_max_active == 1 || wq->rescuer)) + touch_wq_lockdep_map(wq); + rcu_read_unlock(); return true; already_gone: @@ -3403,9 +4201,6 @@ static bool __flush_work(struct work_struct *work, bool from_cancel) if (WARN_ON(!work->func)) return false; - lock_map_acquire(&work->lockdep_map); - lock_map_release(&work->lockdep_map); - if (start_flush_work(work, &barr, from_cancel)) { wait_for_completion(&barr.done); destroy_work_on_stack(&barr.work); @@ -3432,108 +4227,6 @@ bool flush_work(struct work_struct *work) } EXPORT_SYMBOL_GPL(flush_work); -struct cwt_wait { - wait_queue_entry_t wait; - struct work_struct *work; -}; - -static int cwt_wakefn(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) -{ - struct cwt_wait *cwait = container_of(wait, struct cwt_wait, wait); - - if (cwait->work != key) - return 0; - return autoremove_wake_function(wait, mode, sync, key); -} - -static bool __cancel_work_timer(struct work_struct *work, bool is_dwork) -{ - static DECLARE_WAIT_QUEUE_HEAD(cancel_waitq); - unsigned long flags; - int ret; - - do { - ret = try_to_grab_pending(work, is_dwork, &flags); - /* - * If someone else is already canceling, wait for it to - * finish. flush_work() doesn't work for PREEMPT_NONE - * because we may get scheduled between @work's completion - * and the other canceling task resuming and clearing - * CANCELING - flush_work() will return false immediately - * as @work is no longer busy, try_to_grab_pending() will - * return -ENOENT as @work is still being canceled and the - * other canceling task won't be able to clear CANCELING as - * we're hogging the CPU. - * - * Let's wait for completion using a waitqueue. As this - * may lead to the thundering herd problem, use a custom - * wake function which matches @work along with exclusive - * wait and wakeup. - */ - if (unlikely(ret == -ENOENT)) { - struct cwt_wait cwait; - - init_wait(&cwait.wait); - cwait.wait.func = cwt_wakefn; - cwait.work = work; - - prepare_to_wait_exclusive(&cancel_waitq, &cwait.wait, - TASK_UNINTERRUPTIBLE); - if (work_is_canceling(work)) - schedule(); - finish_wait(&cancel_waitq, &cwait.wait); - } - } while (unlikely(ret < 0)); - - /* tell other tasks trying to grab @work to back off */ - mark_work_canceling(work); - local_irq_restore(flags); - - /* - * This allows canceling during early boot. We know that @work - * isn't executing. - */ - if (wq_online) - __flush_work(work, true); - - clear_work_data(work); - - /* - * Paired with prepare_to_wait() above so that either - * waitqueue_active() is visible here or !work_is_canceling() is - * visible there. - */ - smp_mb(); - if (waitqueue_active(&cancel_waitq)) - __wake_up(&cancel_waitq, TASK_NORMAL, 1, work); - - return ret; -} - -/** - * cancel_work_sync - cancel a work and wait for it to finish - * @work: the work to cancel - * - * Cancel @work and wait for its execution to finish. This function - * can be used even if the work re-queues itself or migrates to - * another workqueue. On return from this function, @work is - * guaranteed to be not pending or executing on any CPU. - * - * cancel_work_sync(&delayed_work->work) must not be used for - * delayed_work's. Use cancel_delayed_work_sync() instead. - * - * The caller must ensure that the workqueue on which @work was last - * queued can't be destroyed before this function returns. - * - * Return: - * %true if @work was pending, %false otherwise. - */ -bool cancel_work_sync(struct work_struct *work) -{ - return __cancel_work_timer(work, false); -} -EXPORT_SYMBOL_GPL(cancel_work_sync); - /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush @@ -3576,20 +4269,50 @@ bool flush_rcu_work(struct rcu_work *rwork) } EXPORT_SYMBOL(flush_rcu_work); -static bool __cancel_work(struct work_struct *work, bool is_dwork) +static bool __cancel_work(struct work_struct *work, u32 cflags) { - unsigned long flags; + unsigned long irq_flags; int ret; do { - ret = try_to_grab_pending(work, is_dwork, &flags); + ret = try_to_grab_pending(work, cflags, &irq_flags); } while (unlikely(ret == -EAGAIN)); if (unlikely(ret < 0)) return false; - set_work_pool_and_clear_pending(work, get_work_pool_id(work)); - local_irq_restore(flags); + set_work_pool_and_clear_pending(work, get_work_pool_id(work), 0); + local_irq_restore(irq_flags); + return ret; +} + +static bool __cancel_work_sync(struct work_struct *work, u32 cflags) +{ + unsigned long irq_flags; + bool ret; + + /* claim @work and tell other tasks trying to grab @work to back off */ + ret = work_grab_pending(work, cflags, &irq_flags); + mark_work_canceling(work); + local_irq_restore(irq_flags); + + /* + * Skip __flush_work() during early boot when we know that @work isn't + * executing. This allows canceling during early boot. + */ + if (wq_online) + __flush_work(work, true); + + /* + * smp_mb() at the end of set_work_pool_and_clear_pending() is paired + * with prepare_to_wait() above so that either waitqueue_active() is + * visible here or !work_is_canceling() is visible there. + */ + set_work_pool_and_clear_pending(work, WORK_OFFQ_POOL_NONE, 0); + + if (waitqueue_active(&wq_cancel_waitq)) + __wake_up(&wq_cancel_waitq, TASK_NORMAL, 1, work); + return ret; } @@ -3598,11 +4321,35 @@ static bool __cancel_work(struct work_struct *work, bool is_dwork) */ bool cancel_work(struct work_struct *work) { - return __cancel_work(work, false); + return __cancel_work(work, 0); } EXPORT_SYMBOL(cancel_work); /** + * cancel_work_sync - cancel a work and wait for it to finish + * @work: the work to cancel + * + * Cancel @work and wait for its execution to finish. This function + * can be used even if the work re-queues itself or migrates to + * another workqueue. On return from this function, @work is + * guaranteed to be not pending or executing on any CPU. + * + * cancel_work_sync(&delayed_work->work) must not be used for + * delayed_work's. Use cancel_delayed_work_sync() instead. + * + * The caller must ensure that the workqueue on which @work was last + * queued can't be destroyed before this function returns. + * + * Return: + * %true if @work was pending, %false otherwise. + */ +bool cancel_work_sync(struct work_struct *work) +{ + return __cancel_work_sync(work, 0); +} +EXPORT_SYMBOL_GPL(cancel_work_sync); + +/** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * @@ -3620,7 +4367,7 @@ EXPORT_SYMBOL(cancel_work); */ bool cancel_delayed_work(struct delayed_work *dwork) { - return __cancel_work(&dwork->work, true); + return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work); @@ -3635,7 +4382,7 @@ EXPORT_SYMBOL(cancel_delayed_work); */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { - return __cancel_work_timer(&dwork->work, true); + return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work_sync); @@ -3927,11 +4674,66 @@ static void wq_free_lockdep(struct workqueue_struct *wq) } #endif +static void free_node_nr_active(struct wq_node_nr_active **nna_ar) +{ + int node; + + for_each_node(node) { + kfree(nna_ar[node]); + nna_ar[node] = NULL; + } + + kfree(nna_ar[nr_node_ids]); + nna_ar[nr_node_ids] = NULL; +} + +static void init_node_nr_active(struct wq_node_nr_active *nna) +{ + nna->max = WQ_DFL_MIN_ACTIVE; + atomic_set(&nna->nr, 0); + raw_spin_lock_init(&nna->lock); + INIT_LIST_HEAD(&nna->pending_pwqs); +} + +/* + * Each node's nr_active counter will be accessed mostly from its own node and + * should be allocated in the node. + */ +static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar) +{ + struct wq_node_nr_active *nna; + int node; + + for_each_node(node) { + nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node); + if (!nna) + goto err_free; + init_node_nr_active(nna); + nna_ar[node] = nna; + } + + /* [nr_node_ids] is used as the fallback */ + nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE); + if (!nna) + goto err_free; + init_node_nr_active(nna); + nna_ar[nr_node_ids] = nna; + + return 0; + +err_free: + free_node_nr_active(nna_ar); + return -ENOMEM; +} + static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); + if (wq->flags & WQ_UNBOUND) + free_node_nr_active(wq->node_nr_active); + wq_free_lockdep(wq); free_percpu(wq->cpu_pwq); free_workqueue_attrs(wq->unbound_attrs); @@ -4121,6 +4923,13 @@ static void pwq_release_workfn(struct kthread_work *work) mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); + + /* + * For ordered workqueue with a plugged dfl_pwq, restart it now. + */ + if (!is_last && (wq->flags & __WQ_ORDERED)) + unplug_oldest_pwq(wq); + mutex_unlock(&wq->mutex); } @@ -4130,6 +4939,15 @@ static void pwq_release_workfn(struct kthread_work *work) mutex_unlock(&wq_pool_mutex); } + if (!list_empty(&pwq->pending_node)) { + struct wq_node_nr_active *nna = + wq_node_nr_active(pwq->wq, pwq->pool->node); + + raw_spin_lock_irq(&nna->lock); + list_del_init(&pwq->pending_node); + raw_spin_unlock_irq(&nna->lock); + } + call_rcu(&pwq->rcu, rcu_free_pwq); /* @@ -4142,55 +4960,11 @@ static void pwq_release_workfn(struct kthread_work *work) } } -/** - * pwq_adjust_max_active - update a pwq's max_active to the current setting - * @pwq: target pool_workqueue - * - * If @pwq isn't freezing, set @pwq->max_active to the associated - * workqueue's saved_max_active and activate inactive work items - * accordingly. If @pwq is freezing, clear @pwq->max_active to zero. - */ -static void pwq_adjust_max_active(struct pool_workqueue *pwq) -{ - struct workqueue_struct *wq = pwq->wq; - bool freezable = wq->flags & WQ_FREEZABLE; - unsigned long flags; - - /* for @wq->saved_max_active */ - lockdep_assert_held(&wq->mutex); - - /* fast exit for non-freezable wqs */ - if (!freezable && pwq->max_active == wq->saved_max_active) - return; - - /* this function can be called during early boot w/ irq disabled */ - raw_spin_lock_irqsave(&pwq->pool->lock, flags); - - /* - * During [un]freezing, the caller is responsible for ensuring that - * this function is called at least once after @workqueue_freezing - * is updated and visible. - */ - if (!freezable || !workqueue_freezing) { - pwq->max_active = wq->saved_max_active; - - while (!list_empty(&pwq->inactive_works) && - pwq->nr_active < pwq->max_active) - pwq_activate_first_inactive(pwq); - - kick_pool(pwq->pool); - } else { - pwq->max_active = 0; - } - - raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); -} - /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { - BUG_ON((unsigned long)pwq & WORK_STRUCT_FLAG_MASK); + BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK); memset(pwq, 0, sizeof(*pwq)); @@ -4199,6 +4973,7 @@ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); + INIT_LIST_HEAD(&pwq->pending_node); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); @@ -4218,11 +4993,8 @@ static void link_pwq(struct pool_workqueue *pwq) /* set the matching work_color */ pwq->work_color = wq->work_color; - /* sync max_active to the current setting */ - pwq_adjust_max_active(pwq); - /* link in @pwq */ - list_add_rcu(&pwq->pwqs_node, &wq->pwqs); + list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ @@ -4289,10 +5061,11 @@ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu, "possible intersect\n"); } -/* install @pwq into @wq's cpu_pwq and return the old pwq */ +/* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, int cpu, struct pool_workqueue *pwq) { + struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu); struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); @@ -4301,8 +5074,8 @@ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, /* link_pwq() can handle duplicate calls */ link_pwq(pwq); - old_pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu)); - rcu_assign_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu), pwq); + old_pwq = rcu_access_pointer(*slot); + rcu_assign_pointer(*slot, pwq); return old_pwq; } @@ -4383,6 +5156,15 @@ apply_wqattrs_prepare(struct workqueue_struct *wq, cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->attrs = new_attrs; + /* + * For initialized ordered workqueues, there should only be one pwq + * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution + * of newly queued work items until execution of older work items in + * the old pwq's have completed. + */ + if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)) + ctx->dfl_pwq->plugged = true; + ctx->wq = wq; return ctx; @@ -4402,14 +5184,19 @@ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); - /* save the previous pwq and install the new one */ + /* save the previous pwqs and install the new ones */ for_each_possible_cpu(cpu) ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, ctx->pwq_tbl[cpu]); + ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq); + + /* update node_nr_active->max */ + wq_update_node_max_active(ctx->wq, -1); - /* @dfl_pwq might not have been used, ensure it's linked */ - link_pwq(ctx->dfl_pwq); - swap(ctx->wq->dfl_pwq, ctx->dfl_pwq); + /* rescuer needs to respect wq cpumask changes */ + if (ctx->wq->rescuer) + set_cpus_allowed_ptr(ctx->wq->rescuer->task, + unbound_effective_cpumask(ctx->wq)); mutex_unlock(&ctx->wq->mutex); } @@ -4423,14 +5210,6 @@ static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; - /* creating multiple pwqs breaks ordering guarantee */ - if (!list_empty(&wq->pwqs)) { - if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) - return -EINVAL; - - wq->flags &= ~__WQ_ORDERED; - } - ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (IS_ERR(ctx)) return PTR_ERR(ctx); @@ -4519,9 +5298,7 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu, /* nothing to do if the target cpumask matches the current pwq */ wq_calc_pod_cpumask(target_attrs, cpu, off_cpu); - pwq = rcu_dereference_protected(*per_cpu_ptr(wq->cpu_pwq, cpu), - lockdep_is_held(&wq_pool_mutex)); - if (wqattrs_equal(target_attrs, pwq->pool->attrs)) + if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs)) return; /* create a new pwq */ @@ -4539,10 +5316,11 @@ static void wq_update_pod(struct workqueue_struct *wq, int cpu, use_dfl_pwq: mutex_lock(&wq->mutex); - raw_spin_lock_irq(&wq->dfl_pwq->pool->lock); - get_pwq(wq->dfl_pwq); - raw_spin_unlock_irq(&wq->dfl_pwq->pool->lock); - old_pwq = install_unbound_pwq(wq, cpu, wq->dfl_pwq); + pwq = unbound_pwq(wq, -1); + raw_spin_lock_irq(&pwq->pool->lock); + get_pwq(pwq); + raw_spin_unlock_irq(&pwq->pool->lock); + old_pwq = install_unbound_pwq(wq, cpu, pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); @@ -4559,10 +5337,17 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) if (!(wq->flags & WQ_UNBOUND)) { for_each_possible_cpu(cpu) { - struct pool_workqueue **pwq_p = - per_cpu_ptr(wq->cpu_pwq, cpu); - struct worker_pool *pool = - &(per_cpu_ptr(cpu_worker_pools, cpu)[highpri]); + struct pool_workqueue **pwq_p; + struct worker_pool __percpu *pools; + struct worker_pool *pool; + + if (wq->flags & WQ_BH) + pools = bh_worker_pools; + else + pools = cpu_worker_pools; + + pool = &(per_cpu_ptr(pools, cpu)[highpri]); + pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); @@ -4580,10 +5365,13 @@ static int alloc_and_link_pwqs(struct workqueue_struct *wq) cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { + struct pool_workqueue *dfl_pwq; + ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ - WARN(!ret && (wq->pwqs.next != &wq->dfl_pwq->pwqs_node || - wq->pwqs.prev != &wq->dfl_pwq->pwqs_node), + dfl_pwq = rcu_access_pointer(wq->dfl_pwq); + WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || + wq->pwqs.prev != &dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); @@ -4652,12 +5440,78 @@ static int init_rescuer(struct workqueue_struct *wq) } wq->rescuer = rescuer; - kthread_bind_mask(rescuer->task, cpu_possible_mask); + if (wq->flags & WQ_UNBOUND) + kthread_bind_mask(rescuer->task, wq_unbound_cpumask); + else + kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } +/** + * wq_adjust_max_active - update a wq's max_active to the current setting + * @wq: target workqueue + * + * If @wq isn't freezing, set @wq->max_active to the saved_max_active and + * activate inactive work items accordingly. If @wq is freezing, clear + * @wq->max_active to zero. + */ +static void wq_adjust_max_active(struct workqueue_struct *wq) +{ + bool activated; + int new_max, new_min; + + lockdep_assert_held(&wq->mutex); + + if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) { + new_max = 0; + new_min = 0; + } else { + new_max = wq->saved_max_active; + new_min = wq->saved_min_active; + } + + if (wq->max_active == new_max && wq->min_active == new_min) + return; + + /* + * Update @wq->max/min_active and then kick inactive work items if more + * active work items are allowed. This doesn't break work item ordering + * because new work items are always queued behind existing inactive + * work items if there are any. + */ + WRITE_ONCE(wq->max_active, new_max); + WRITE_ONCE(wq->min_active, new_min); + + if (wq->flags & WQ_UNBOUND) + wq_update_node_max_active(wq, -1); + + if (new_max == 0) + return; + + /* + * Round-robin through pwq's activating the first inactive work item + * until max_active is filled. + */ + do { + struct pool_workqueue *pwq; + + activated = false; + for_each_pwq(pwq, wq) { + unsigned long irq_flags; + + /* can be called during early boot w/ irq disabled */ + raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); + if (pwq_activate_first_inactive(pwq, true)) { + activated = true; + kick_pool(pwq->pool); + } + raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); + } + } while (activated); +} + __printf(1, 4) struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, @@ -4665,23 +5519,27 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, { va_list args; struct workqueue_struct *wq; - struct pool_workqueue *pwq; + size_t wq_size; + int name_len; - /* - * Unbound && max_active == 1 used to imply ordered, which is no longer - * the case on many machines due to per-pod pools. While - * alloc_ordered_workqueue() is the right way to create an ordered - * workqueue, keep the previous behavior to avoid subtle breakages. - */ - if ((flags & WQ_UNBOUND) && max_active == 1) - flags |= __WQ_ORDERED; + if (flags & WQ_BH) { + if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS)) + return NULL; + if (WARN_ON_ONCE(max_active)) + return NULL; + } /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ - wq = kzalloc(sizeof(*wq), GFP_KERNEL); + if (flags & WQ_UNBOUND) + wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1); + else + wq_size = sizeof(*wq); + + wq = kzalloc(wq_size, GFP_KERNEL); if (!wq) return NULL; @@ -4692,15 +5550,30 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, } va_start(args, max_active); - vsnprintf(wq->name, sizeof(wq->name), fmt, args); + name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); va_end(args); - max_active = max_active ?: WQ_DFL_ACTIVE; - max_active = wq_clamp_max_active(max_active, flags, wq->name); + if (name_len >= WQ_NAME_LEN) + pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", + wq->name); + + if (flags & WQ_BH) { + /* + * BH workqueues always share a single execution context per CPU + * and don't impose any max_active limit. + */ + max_active = INT_MAX; + } else { + max_active = max_active ?: WQ_DFL_ACTIVE; + max_active = wq_clamp_max_active(max_active, flags, wq->name); + } /* init wq */ wq->flags = flags; - wq->saved_max_active = max_active; + wq->max_active = max_active; + wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE); + wq->saved_max_active = wq->max_active; + wq->saved_min_active = wq->min_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); @@ -4711,8 +5584,13 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, wq_init_lockdep(wq); INIT_LIST_HEAD(&wq->list); + if (flags & WQ_UNBOUND) { + if (alloc_node_nr_active(wq->node_nr_active) < 0) + goto err_unreg_lockdep; + } + if (alloc_and_link_pwqs(wq) < 0) - goto err_unreg_lockdep; + goto err_free_node_nr_active; if (wq_online && init_rescuer(wq) < 0) goto err_destroy; @@ -4728,8 +5606,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); - for_each_pwq(pwq, wq) - pwq_adjust_max_active(pwq); + wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); @@ -4738,6 +5615,9 @@ struct workqueue_struct *alloc_workqueue(const char *fmt, return wq; +err_free_node_nr_active: + if (wq->flags & WQ_UNBOUND) + free_node_nr_active(wq->node_nr_active); err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); @@ -4759,9 +5639,9 @@ static bool pwq_busy(struct pool_workqueue *pwq) if (pwq->nr_in_flight[i]) return true; - if ((pwq != pwq->wq->dfl_pwq) && (pwq->refcnt > 1)) + if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1)) return true; - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) + if (!pwq_is_empty(pwq)) return true; return false; @@ -4843,13 +5723,12 @@ void destroy_workqueue(struct workqueue_struct *wq) rcu_read_lock(); for_each_possible_cpu(cpu) { - pwq = rcu_access_pointer(*per_cpu_ptr(wq->cpu_pwq, cpu)); - RCU_INIT_POINTER(*per_cpu_ptr(wq->cpu_pwq, cpu), NULL); - put_pwq_unlocked(pwq); + put_pwq_unlocked(unbound_pwq(wq, cpu)); + RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL); } - put_pwq_unlocked(wq->dfl_pwq); - wq->dfl_pwq = NULL; + put_pwq_unlocked(unbound_pwq(wq, -1)); + RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL); rcu_read_unlock(); } @@ -4860,34 +5739,63 @@ EXPORT_SYMBOL_GPL(destroy_workqueue); * @wq: target workqueue * @max_active: new max_active value. * - * Set max_active of @wq to @max_active. + * Set max_active of @wq to @max_active. See the alloc_workqueue() function + * comment. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { - struct pool_workqueue *pwq; - + /* max_active doesn't mean anything for BH workqueues */ + if (WARN_ON(wq->flags & WQ_BH)) + return; /* disallow meddling with max_active for ordered workqueues */ - if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) + if (WARN_ON(wq->flags & __WQ_ORDERED)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); - wq->flags &= ~__WQ_ORDERED; wq->saved_max_active = max_active; + if (wq->flags & WQ_UNBOUND) + wq->saved_min_active = min(wq->saved_min_active, max_active); - for_each_pwq(pwq, wq) - pwq_adjust_max_active(pwq); + wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** + * workqueue_set_min_active - adjust min_active of an unbound workqueue + * @wq: target unbound workqueue + * @min_active: new min_active value + * + * Set min_active of an unbound workqueue. Unlike other types of workqueues, an + * unbound workqueue is not guaranteed to be able to process max_active + * interdependent work items. Instead, an unbound workqueue is guaranteed to be + * able to process min_active number of interdependent work items which is + * %WQ_DFL_MIN_ACTIVE by default. + * + * Use this function to adjust the min_active value between 0 and the current + * max_active. + */ +void workqueue_set_min_active(struct workqueue_struct *wq, int min_active) +{ + /* min_active is only meaningful for non-ordered unbound workqueues */ + if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) != + WQ_UNBOUND)) + return; + + mutex_lock(&wq->mutex); + wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active); + wq_adjust_max_active(wq); + mutex_unlock(&wq->mutex); +} + +/** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. @@ -4972,7 +5880,7 @@ EXPORT_SYMBOL_GPL(workqueue_congested); unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; - unsigned long flags; + unsigned long irq_flags; unsigned int ret = 0; if (work_pending(work)) @@ -4981,10 +5889,10 @@ unsigned int work_busy(struct work_struct *work) rcu_read_lock(); pool = get_work_pool(work); if (pool) { - raw_spin_lock_irqsave(&pool->lock, flags); + raw_spin_lock_irqsave(&pool->lock, irq_flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; - raw_spin_unlock_irqrestore(&pool->lock, flags); + raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } rcu_read_unlock(); @@ -5069,7 +5977,24 @@ static void pr_cont_pool_info(struct worker_pool *pool) pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); - pr_cont(" flags=0x%x nice=%d", pool->flags, pool->attrs->nice); + pr_cont(" flags=0x%x", pool->flags); + if (pool->flags & POOL_BH) + pr_cont(" bh%s", + pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); + else + pr_cont(" nice=%d", pool->attrs->nice); +} + +static void pr_cont_worker_id(struct worker *worker) +{ + struct worker_pool *pool = worker->pool; + + if (pool->flags & WQ_BH) + pr_cont("bh%s", + pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); + else + pr_cont("%d%s", task_pid_nr(worker->task), + worker->rescue_wq ? "(RESCUER)" : ""); } struct pr_cont_work_struct { @@ -5128,8 +6053,8 @@ static void show_pwq(struct pool_workqueue *pwq) pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); - pr_cont(" active=%d/%d refcnt=%d%s\n", - pwq->nr_active, pwq->max_active, pwq->refcnt, + pr_cont(" active=%d refcnt=%d%s\n", + pwq->nr_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { @@ -5146,10 +6071,9 @@ static void show_pwq(struct pool_workqueue *pwq) if (worker->current_pwq != pwq) continue; - pr_cont("%s %d%s:%ps", comma ? "," : "", - task_pid_nr(worker->task), - worker->rescue_wq ? "(RESCUER)" : "", - worker->current_func); + pr_cont(" %s", comma ? "," : ""); + pr_cont_worker_id(worker); + pr_cont(":%ps", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); @@ -5200,10 +6124,10 @@ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; - unsigned long flags; + unsigned long irq_flags; for_each_pwq(pwq, wq) { - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { + if (!pwq_is_empty(pwq)) { idle = false; break; } @@ -5214,8 +6138,8 @@ void show_one_workqueue(struct workqueue_struct *wq) pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { - raw_spin_lock_irqsave(&pwq->pool->lock, flags); - if (pwq->nr_active || !list_empty(&pwq->inactive_works)) { + raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); + if (!pwq_is_empty(pwq)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks @@ -5225,7 +6149,7 @@ void show_one_workqueue(struct workqueue_struct *wq) show_pwq(pwq); printk_deferred_exit(); } - raw_spin_unlock_irqrestore(&pwq->pool->lock, flags); + raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering @@ -5244,10 +6168,10 @@ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; - unsigned long flags; + unsigned long irq_flags; unsigned long hung = 0; - raw_spin_lock_irqsave(&pool->lock, flags); + raw_spin_lock_irqsave(&pool->lock, irq_flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; @@ -5268,14 +6192,14 @@ static void show_one_worker_pool(struct worker_pool *pool) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { - pr_cont(" %s%d", first ? "idle: " : "", - task_pid_nr(worker->task)); + pr_cont(" %s", first ? "idle: " : ""); + pr_cont_worker_id(worker); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: - raw_spin_unlock_irqrestore(&pool->lock, flags); + raw_spin_unlock_irqrestore(&pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering @@ -5542,13 +6466,15 @@ int workqueue_online_cpu(unsigned int cpu) mutex_lock(&wq_pool_mutex); for_each_pool(pool, pi) { - mutex_lock(&wq_pool_attach_mutex); + /* BH pools aren't affected by hotplug */ + if (pool->flags & POOL_BH) + continue; + mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); - mutex_unlock(&wq_pool_attach_mutex); } @@ -5562,6 +6488,10 @@ int workqueue_online_cpu(unsigned int cpu) for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) wq_update_pod(wq, tcpu, cpu, true); + + mutex_lock(&wq->mutex); + wq_update_node_max_active(wq, -1); + mutex_unlock(&wq->mutex); } } @@ -5590,6 +6520,10 @@ int workqueue_offline_cpu(unsigned int cpu) for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) wq_update_pod(wq, tcpu, cpu, false); + + mutex_lock(&wq->mutex); + wq_update_node_max_active(wq, cpu); + mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); @@ -5677,7 +6611,6 @@ EXPORT_SYMBOL_GPL(work_on_cpu_safe_key); void freeze_workqueues_begin(void) { struct workqueue_struct *wq; - struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); @@ -5686,8 +6619,7 @@ void freeze_workqueues_begin(void) list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); - for_each_pwq(pwq, wq) - pwq_adjust_max_active(pwq); + wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } @@ -5752,7 +6684,6 @@ out_unlock: void thaw_workqueues(void) { struct workqueue_struct *wq; - struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); @@ -5764,8 +6695,7 @@ void thaw_workqueues(void) /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); - for_each_pwq(pwq, wq) - pwq_adjust_max_active(pwq); + wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } @@ -5784,16 +6714,9 @@ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { - if (!(wq->flags & WQ_UNBOUND)) + if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING)) continue; - /* creating multiple pwqs breaks ordering guarantee */ - if (!list_empty(&wq->pwqs)) { - if (wq->flags & __WQ_ORDERED_EXPLICIT) - continue; - wq->flags &= ~__WQ_ORDERED; - } - ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); @@ -6307,11 +7230,10 @@ int workqueue_sysfs_register(struct workqueue_struct *wq) int ret; /* - * Adjusting max_active or creating new pwqs by applying - * attributes breaks ordering guarantee. Disallow exposing ordered - * workqueues. + * Adjusting max_active breaks ordering guarantee. Disallow exposing + * ordered workqueues. */ - if (WARN_ON(wq->flags & __WQ_ORDERED_EXPLICIT)) + if (WARN_ON(wq->flags & __WQ_ORDERED)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); @@ -6408,10 +7330,10 @@ static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; static void show_cpu_pool_hog(struct worker_pool *pool) { struct worker *worker; - unsigned long flags; + unsigned long irq_flags; int bkt; - raw_spin_lock_irqsave(&pool->lock, flags); + raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (task_is_running(worker->task)) { @@ -6429,7 +7351,7 @@ static void show_cpu_pool_hog(struct worker_pool *pool) } } - raw_spin_unlock_irqrestore(&pool->lock, flags); + raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } static void show_cpu_pools_hogs(void) @@ -6501,7 +7423,7 @@ static void wq_watchdog_timer_fn(struct timer_list *unused) /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; - if (pool->cpu >= 0) { + if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) { pool->cpu_stall = true; cpu_pool_stall = true; } @@ -6584,6 +7506,16 @@ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ +static void bh_pool_kick_normal(struct irq_work *irq_work) +{ + raise_softirq_irqoff(TASKLET_SOFTIRQ); +} + +static void bh_pool_kick_highpri(struct irq_work *irq_work) +{ + raise_softirq_irqoff(HI_SOFTIRQ); +} + static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) { if (!cpumask_intersects(wq_unbound_cpumask, mask)) { @@ -6595,6 +7527,22 @@ static void __init restrict_unbound_cpumask(const char *name, const struct cpuma cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); } +static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice) +{ + BUG_ON(init_worker_pool(pool)); + pool->cpu = cpu; + cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); + cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); + pool->attrs->nice = nice; + pool->attrs->affn_strict = true; + pool->node = cpu_to_node(cpu); + + /* alloc pool ID */ + mutex_lock(&wq_pool_mutex); + BUG_ON(worker_pool_assign_id(pool)); + mutex_unlock(&wq_pool_mutex); +} + /** * workqueue_init_early - early init for workqueue subsystem * @@ -6609,6 +7557,8 @@ void __init workqueue_init_early(void) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM]; int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; + void (*irq_work_fns[2])(struct irq_work *) = { bh_pool_kick_normal, + bh_pool_kick_highpri }; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); @@ -6630,6 +7580,13 @@ void __init workqueue_init_early(void) wq_update_pod_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!wq_update_pod_attrs_buf); + /* + * If nohz_full is enabled, set power efficient workqueue as unbound. + * This allows workqueue items to be moved to HK CPUs. + */ + if (housekeeping_enabled(HK_TYPE_TICK)) + wq_power_efficient = true; + /* initialize WQ_AFFN_SYSTEM pods */ pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL); @@ -6643,25 +7600,21 @@ void __init workqueue_init_early(void) pt->pod_node[0] = NUMA_NO_NODE; pt->cpu_pod[0] = 0; - /* initialize CPU pools */ + /* initialize BH and CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; - for_each_cpu_worker_pool(pool, cpu) { - BUG_ON(init_worker_pool(pool)); - pool->cpu = cpu; - cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); - cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); - pool->attrs->nice = std_nice[i++]; - pool->attrs->affn_strict = true; - pool->node = cpu_to_node(cpu); - - /* alloc pool ID */ - mutex_lock(&wq_pool_mutex); - BUG_ON(worker_pool_assign_id(pool)); - mutex_unlock(&wq_pool_mutex); + for_each_bh_worker_pool(pool, cpu) { + init_cpu_worker_pool(pool, cpu, std_nice[i]); + pool->flags |= POOL_BH; + init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]); + i++; } + + i = 0; + for_each_cpu_worker_pool(pool, cpu) + init_cpu_worker_pool(pool, cpu, std_nice[i++]); } /* create default unbound and ordered wq attrs */ @@ -6691,13 +7644,17 @@ void __init workqueue_init_early(void) WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); - system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_power_efficient", + system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); + system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0); + system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", + WQ_BH | WQ_HIGHPRI, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || - !system_freezable_power_efficient_wq); + !system_freezable_power_efficient_wq || + !system_bh_wq || !system_bh_highpri_wq); } static void __init wq_cpu_intensive_thresh_init(void) @@ -6763,9 +7720,10 @@ void __init workqueue_init(void) * up. Also, create a rescuer for workqueues that requested it. */ for_each_possible_cpu(cpu) { - for_each_cpu_worker_pool(pool, cpu) { + for_each_bh_worker_pool(pool, cpu) + pool->node = cpu_to_node(cpu); + for_each_cpu_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); - } } list_for_each_entry(wq, &workqueues, list) { @@ -6776,7 +7734,16 @@ void __init workqueue_init(void) mutex_unlock(&wq_pool_mutex); - /* create the initial workers */ + /* + * Create the initial workers. A BH pool has one pseudo worker that + * represents the shared BH execution context and thus doesn't get + * affected by hotplug events. Create the BH pseudo workers for all + * possible CPUs here. + */ + for_each_possible_cpu(cpu) + for_each_bh_worker_pool(pool, cpu) + BUG_ON(!create_worker(pool)); + for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; @@ -6856,7 +7823,7 @@ static bool __init cpus_share_numa(int cpu0, int cpu1) /** * workqueue_init_topology - initialize CPU pods for unbound workqueues * - * This is the third step of there-staged workqueue subsystem initialization and + * This is the third step of three-staged workqueue subsystem initialization and * invoked after SMP and topology information are fully initialized. It * initializes the unbound CPU pods accordingly. */ @@ -6870,6 +7837,8 @@ void __init workqueue_init_topology(void) init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache); init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa); + wq_topo_initialized = true; + mutex_lock(&wq_pool_mutex); /* @@ -6878,8 +7847,12 @@ void __init workqueue_init_topology(void) * combinations to apply per-pod sharing. */ list_for_each_entry(wq, &workqueues, list) { - for_each_online_cpu(cpu) { + for_each_online_cpu(cpu) wq_update_pod(wq, cpu, cpu, true); + if (wq->flags & WQ_UNBOUND) { + mutex_lock(&wq->mutex); + wq_update_node_max_active(wq, -1); + mutex_unlock(&wq->mutex); } } |